feat: add new posts

.gitignore

@@ -1,3 +1,5 @@
 .secret/
 sitemap.gz
 sitemap.txt
+.wip/*
+blug.md

.subscribe/index.html

@@ -1,9 +1,17 @@
+<!--
+Send me an email to list@nunosempere.com with subject "Subscribe to blog" and your name. 
+
+There previously was a form here, but I think someone was inputting random emails, so that's it for now.
+
+-->
+
+
 <form method="post" action="https://listmonk.nunosempere.com/subscription/form" class="listmonk-form">
     <div>
             <h3>Subscribe</h3>
             <input type="hidden" name="nonce" />
             <p><input type="email" name="email" required placeholder="E-mail" class="subscribe-input"/></p>
-            <p><input type="text" name="name" placeholder="Name (optional)" class="subscribe-input"/></ap>
+            <p><input type="text" name="name" placeholder="Name (helps me filter out malicious entries)" class="subscribe-input"/></ap>
           
             <p>
               <input id="82ff8" type="checkbox" name="l" checked value="82ff889c-f9d9-4a45-bf9a-7e2696813021" />
@@ -13,3 +21,7 @@
         <p><input type="submit" value="Subscribe" class="subscribe-button"/></p>
     </div>
 </form>
+
+<p>
+...or send me an email to list@nunosempere.com with subject "Subscribe to blog" and your name.
+</p>

blog/2022/04/07/openphil-allocation/index.md

@@ -1,4 +1,4 @@
-Open Philanthopy's allocation by cause area
+Open Philanthopy allocation by cause area
 ===========================================
 
 Open Philanthropy's grants so far, roughly:

blog/2022/05/20/infinite-ethics-101/index.md

@@ -66,4 +66,8 @@ I would still say that B is preferable to A in that case. And my impression is t
 
 Exercise for the reader: Come up with two infinite sequences which cannot be compared using statewise or stochastic dominance, or similar principles.
 
-You can comment on this post in the [EA Forum](https://forum.effectivealtruism.org/posts/GseREh8MEEuLCZayf/nunosempere-s-shortform?commentId=BMEaMkB8Fdrz7oanw).
+You can see some discussion of this post in the [EA Forum](https://forum.effectivealtruism.org/posts/GseREh8MEEuLCZayf/nunosempere-s-shortform?commentId=BMEaMkB8Fdrz7oanw).
+
+<p><section id="isso-thread">
+  <noscript>Javascript needs to be activated to view comments.</noscript>
+</section></p>

blog/2022/10/10/five-slightly-more-hardcore-squiggle-models/index.md

@@ -127,7 +127,10 @@ For uncertainty about the number of beneficiaries, we could naïvely write:
 valueWithUncertaintyAboutNumBeneficiaries(num_beneficiaries_dist, population_age_distribution, benefitForPersonOfAge) = {
   numSamples = 1000
   num_beneficiaries_samples_list = sampleN(num_beneficiaries_dist, numSamples)
-  benefits_list = List.map(num_beneficiaries_samples_list, {|n| valueOfInterventionInPopulation(n, population_age_distribution, benefitForPersonOfAge)})
+  benefits_list = List.map(num_beneficiaries_samples_list, 
+    {|n| 
+      valueOfInterventionInPopulation(n, population_age_distribution, benefitForPersonOfAge)
+    })
   result = mixture(benefits_list)
   result
 }
@@ -239,7 +242,11 @@ And then we can specify our amount of funds;
 ```
 availableFunds = 1M // dollars
 calculationIncrement  = 1 // calculate dollar by dollar
-Danger.optimalAllocationGivenDiminishingMarginalReturnsForManyFunctions(listOfDiminishingMarginalReturns, availableFunds, calculationIncrement) 
+Danger.optimalAllocationGivenDiminishingMarginalReturnsForManyFunctions(
+  listOfDiminishingMarginalReturns,
+  availableFunds, 
+  calculationIncrement
+) 
 ```
 
 So in this case, the difficulty comes not from applying a function, but from adding that function to Squiggle. This can be seen [here](https://github.com/quantified-uncertainty/squiggle/blob/develop/packages/squiggle-lang/src/rescript/FR/FR_Danger.res#L278).

blog/2022/12/16/covid-19-in-rural-balochistan-pakistan-two-interviews-from-1/index.md

@@ -0,0 +1,354 @@
+COVID-19 in rural Balochistan, Pakistan: Two interviews from May 2020
+=====================================================================
+
+The interviews were carried out to better inform a team of forecasters and superforecasters working with an organization which was aiming to develop better COVID-19 forecasts early on in the pandemic for countries and regions which didn't have the capability. Said team and I came up with the questions, and the interviews themselves were carried out in Urdu by [Quratulain Zainab](https://forum.effectivealtruism.org/users/qurat) and then translated back to English.
+
+Back then, I think these interviews were fairly valuable in terms of giving more information to our team. Now, more than two years later I'm getting around to sharing this post because it could help readers develop better models of the world, because it may have some relevance to some [philosophical debates](https://forum.effectivealtruism.org/posts/rGA32YnSYGL9QEoj9/guerrilla-foundation-response-to-ea-forum-discussion) around altruism, and because of "[draft amnesty day](https://forum.effectivealtruism.org/posts/vHogKj87ZBLgN8TpQ/today-is-draft-amnesty-day-december-16-18)".
+
+## Interview 1.
+
+The conversation was with Najeeb from Loralai, Balochistan. This is a translation from Urdu. The translator, Quratulain, would like to specify that they don’t talk exactly like this. The interview was carried out on the 12th of May of 2020.
+
+Q: Where are you from in Balochistan? City or village?
+
+N: I’m from Balochistan’s Larolai district, it’s 5 km from the city
+
+Q: Okay. In your area, how many people live in each house?
+
+N: There's a combined family system here. In each house, an average of 15-20 people. In some houses, up to 30-40. I told you the average.
+
+Q: How much distance is there between each house?
+
+N: There’s no distances. Attached houses.
+
+Q: What do people there think about coronavirus? Are they worried about it or not so much? What do you yourself think about it?
+
+N: Our city is almost Balochistan’s second largest city. Over here, 90% of people don’t accept that coronavirus could even affect them. Some say that yes, coronavirus exists on a world level but not in our city. There’s no case yet in our city.
+
+Q: Yes, okay. Is there anything being done there to increase social distancing or sanitation?
+
+N: Government tries it but the public gives no response. Government is tired.
+
+Q: Ok. What things did the government try to do?
+
+N: To make shutdown better, the government has tried a lot. Often shops have circles for distance, there’s printed material and wall chalking for awareness
+
+Q: Meaning of wall chalking?
+
+N: In villages, spreading awareness about precautionary measures against coronavirus
+
+Q: Do shops and people follow this? And how strict is the government / police on this? Ok. How do you know about the villages?
+
+N: \[They are strict\] to a large extent. I myself live in a village.
+
+Q: Oh. You live in a village?
+
+N: Yes
+
+Q: So people are still following the rules?
+
+N: Right now, before 5 pm there’s complete freedom. After 5 pm, the government forces all shops to close. For the rest of the village, there’s complete freedom. Because over here, there’s no patient yet so people don’t take it that seriously
+
+Q: In people’s opinion, should there be more freedom? Before 5 PM all shops are open and after 5 PM all shops are closed?
+
+N: People say that no one has been affected by it yet so why should there be such strictness. Yes.
+
+Q: In the shops, are people close together or are they maintaining social distance because of the circles?
+
+N: They are close together
+
+Q: But they can’t go to shops after 5 pm? But they can meet their friends outside?
+
+N: Yes. Only shops are closed. Otherwise, they can meet.
+
+Q: Over the previous weeks, did you have any interaction with the medical system?
+
+N: Yes I went \[to a hospital\]. CMH. 4 times in a week
+
+Q: For what reason, if you want to say?
+
+N: My nephew was ill. I took him there.
+
+Q: What do you think about the hospitals there?
+
+N: You must already know about CMH. 100 (emoji) was ok.
+
+Q: What type of illness \[about the nephew\]
+
+N: very severe fever. For many years. Even last year, and this year. So I took him for a check up.
+
+Q: Is he fine now?
+
+N: yes, yes
+
+Q: ok
+
+N: yes
+
+Q: Are tests being conducted there for coronavirus in hospitals?
+
+N: Sorry! I don’t know. Maybe they are happening but not confirmed
+
+Q: Ok
+
+N: Yes
+
+Q: So if someone is afraid that they have the virus, what would they do?
+
+N: For them, there are preparations done by hospitals. They’ll be isolated. Then a test will be done. Government has made isolation wards. In civil hospital
+
+Q: In your opinion, hospitals / government are able to handle the isolation well?
+
+N: Yes. Because if in the houses, someone gets the virus, then they can’t provide better isolation. So in my opinion, the hospital will be better.
+
+Q: In your opinion, do the hospitals have enough masks / tests etc to deal with this situation?
+
+N: Yes
+
+Q: Okay. In your area, did you hear of any unexplained sickness or death? Do you know of anyone who might have covid?
+
+N: No. No deaths in the city. I don’t know anyone personally who has the virus.
+
+Q: Ok. Are mosques open there?
+
+N: 100 (emoji)
+
+Q: If they are open, how often do people go?
+
+N: it’s pretty obvious 5 times \[a day\]
+
+Q: In your opinion, should they remain open?
+
+N: In my opinion, not in the city. But they should definitely be open in the villages. Because in villages, no one comes from outside. In the city, people come from different areas
+
+Q: Ok. No one comes from outside to your village?
+
+N: Very few people come from outside the village
+
+Q: But visitors from outside do come?
+
+N: Yes
+
+Q: Ok. In one mosque, at one time (like for Friday prayers), how many people gather?
+
+N: Other than Friday prayer, on average 25-30 people. For Friday prayers, more than 150
+
+Q: And this is without distancing?
+
+N: Yes
+
+Q: What do people there think about how to treat covid cases?
+
+N: There’s no treatment
+
+Q: What do people think about how to deal with covid cases? Are there any superstitions about this?
+
+N: Sorry I don’t know about this, what people think.
+
+Q: Ok, no problem. What do you think about it?
+
+N: Isolate them, provide a clean environment, give them the medicine etc, with time it will get better
+
+Q: Ok. Do people there wear masks? Are there any laws about this?
+
+N: In government offices, people wear masks. Otherwise, 80% of public doesn’t
+
+Q: People can buy masks in shops?
+
+N: Yes, they are available in pharmacies
+
+Q: Do people make masks at home? Have you yourself made / worn a mask?
+
+N: \[about making masks at home\] there was no need
+
+Q: Ok
+
+N: I wear a mask. Haven’t made it myself.
+
+Q: Can people buy masks at a reasonable price at the pharmacy?
+
+N: Yes
+
+Q: Have people’s jobs been affected because of shutdowns due to the virus?
+
+N: Labourers have been affected
+
+Q: What do they do now?
+
+N: Now, they go to work. Before, people helped them.
+
+Q: In the city? But in your opinion, people have been largely unaffected financially?
+
+N: Yes.
+
+Q: What do you think about the Baloch nationalists?
+
+N: I don’t know about this. In our area, there’s no such thing. Only pashtuns live here.
+
+Q: Ok. In your opinion, how well is Pakistani government handling the covid situation?
+
+N: Yes, they’re doing well. To a large extent.
+
+Q: The Balochistan government as well?
+
+N: Yes
+
+Q: What do you think about the quality of CMH hospital?
+
+N: Very satisfied
+
+Q: If the virus spread a lot more, do you think the government would still be able to handle it well?
+
+N: yes, when the public supports the government
+
+Q: Ok. What do you think the chances are of you or your close relatives getting coronavirus this year?
+
+N: Very little. This is my opinion but Allah knows best. I’m not giving a governmental report, all of this is just my opinion
+
+Q: of course
+
+N: I can be 100% wrong or 100% correct so it is not official
+
+Q: Okay. Do you have any other thoughts on the topic?
+
+N: No, this was it
+
+Q: Okay. Thank you so much for taking the time to answer these questions. Thanks!
+
+N: No problem. Thank Usman bhai \[friend/bro of Usman\]
+
+Q: Bye
+
+N: Bye
+
+## Interview 2.
+
+The person interviewed is the Makran division head for a non-profit that operates nationally, providing supplies of food all over the country to people whose livelihoods have been affected due to COVID-19. He lives in Turbat, Makran in Balochistan. The interview was carried out on the 18th of May of 2020.
+
+Q: What type of area do you live in? Is it a city or a village?
+
+M: I live in a city but otherwise my connection is to the rural area Dasht.
+
+Q: In your area, how many people live in one house?
+
+M: Minimum five and many have a joint family system as well. From 10-12 people.
+
+Q: What do people there think of coronavirus? Do they worry about it a lot or not so much? What do you yourself think about it?
+
+M: People are very worried about this virus. People's daily lives are greatly affected. Shops and markets are closed. The economic condition of the people is ruined. The government has turned lockdown into smart lockdown. But it is not being implemented by the public. Because the government is not helping the people. In Balochistan, there is no test facility in any city except Quetta. So far some cases have been reported in Makran, Gwadar and Panjgur. No cases have been reported in Turbat division.
+
+Q: Is there anything being done there to increase social distancing and sanitation?
+
+M: No.
+
+Q: Are markets open? How crowded are they? Where do people buy food?
+
+M: The shops are mostly all open here. People do not maintain distancing in the market.
+
+The shops are closed now after 5 o'clock so there is a lot of crowding before
+
+Q: Have you visited a hospital in the past few weeks or have any interaction with the medical system or with doctors?
+
+M: Yes, I went to the hospital. I am in constant contact with doctors every day.
+
+Q: What is your opinion of the healthcare system? Are there tests happening in your area for covid?
+
+M: Doctors aren’t doing their duty in government hospitals but private clinics are quite crowded.
+
+No, there is no test laboratory or facility.
+
+Q: How often do people get fevers? When was the last time you or a friend had a fever? Do you know the reason for that fever?
+
+M: I had a fever before Ramadan and recovered in a couple of days. I only took Panadol
+
+Q: Have you heard of any unexplained illnesses or deaths in your area? Do you know of anyone who you think might have covid-19?
+
+M: No, this has not happened in our area yet. There isn’t any facility for testing so who knows, someone might have coronavirus.
+
+Q: Are mosques open there? What do people think about whether the mosques should be open? If the government tries to close mosques, what do you think will happen?
+
+M: Mosques were closed in the beginning but are now open. People here are against closing mosques
+
+Q: At one time, how many people gather in a mosque?
+
+M: On Fridays the mosques are packed and the rest of the time there are are two to four rows
+
+Q: Is there any local knowledge about how to deal with covid cases? Are there any superstitions about this?
+
+M: People are self-quarantining. People who are less educated are more worried about this virus. However, educated people are not bothered by this, they just follow the instructions of the doctors
+
+Q: Do people wear masks there? Are there any laws for this? Are people making masks at home? Have you yourself made or worn a mask?
+
+M: Yes, they do. I wear masks too. People have made their own masks as well. I haven't made my own. The Balochistan government has prohibited people from going out without wearing a mask.
+
+Q: Are the people who go out without a mask fined or punished in some way?
+
+M: No, this doesn’t happen.
+
+Q: Are people meeting with their friends outside? Or having iftar at home with their friends? Do you think people will gather with their relatives and friends during Eid? By your estimate, what percentage of people wear masks outside?
+
+M: Yes, definitely we meet our friends every day. Iftar gatherings have also been happening. I have been breaking my fast with a friend every day since Ramadan started. The situation here is that people will gather \[for Eid\]. 20% of people \[wear masks\]. There have been many funerals during this time and hundreds of people have attended. Due to corona, religious tendencies have increased. People have started going to mosques more.
+
+Q: Why so many funerals? Are people falling more ill during this time?
+
+M: No, because of old age. This is a picture of an iftar today, only two people are wearing masks. \[Attached was a photo of 13 men sitting close together, two wearing masks but these weren’t covering their mouth or nose so that they could talk\]
+
+Q: What type of sickness in old age, if you know?
+
+M: Diabetes, cancer, kidney, liver etc. Tuberculosis. There are no health facilities in Makran at all. Karachi is beyond the reach of the people
+
+Q: Do any of them require a ventilator?
+
+M: They do but ventilators are not available in Makran. If necessary, doctors refer the patient to Karachi. Due to lack of facilities, most patients die on the way. Makran does not yet have a good ambulance service, either provided by government or private service.
+
+Q: Is the number of deaths now greater than, less than or the same as before?
+
+M: Same as before, there has been no significant increase or decrease in our areas.
+
+Q: Have people’s jobs been affected due to the virus and the lockdowns?
+
+M: Government jobs have not been affected, but labourers and daily wagers are worried. People who work in shops are worried. Government employees are living in luxury, they are getting paid and as all the offices are closed, they are on holiday.
+
+Q: What are the people who’ve lost their jobs doing now?
+
+M: This has rarely happened in our area. Those who are unemployed now are sitting at home.
+
+Q: What is your opinion of Baloch nationalists and the army in the area due to the nationalists?
+
+M: The Pakistan army is present everywhere in Balochistan. Things were very bad a couple years ago, now thank God they are very good. As FC (Frontier Corps) or as something else, but the army is everywhere. The influence of the Baloch Nationalists has diminished. The situation is bad everywhere though, such events keep happening.
+
+Q: Do you think the situation with the baloch nationalists is going to affect how the epidemic plays out?
+
+M: No that won’t happen.
+
+Q: In your opinion, how well is the Pakistani government handling the covid situation? What about the Balochistan government?
+
+M: Both are not handling it well. Turbat is the second largest city in Balochistan yet there is no testing facility or other arrangements provided by the government. Leave aside ventilators, there aren’t even testing kits.
+
+Q: How likely do you think it is you or your close relatives will get the coronavirus this year?
+
+M: I think there is very little chance of that because this has not happened so far here so it isn’t likely.
+
+Q: Do you have any other thoughts on this you’d like to share?
+
+M: \[A prayer against the virus\]
+
+Q: Thank you so much for taking the time to answer all of this :)
+
+M: Thank you. We’re willing to help any time with any work or information you require.
+
+Q: Thank you so much. Bye.
+
+M: Bye.
+
+M: Hi. I forgot to mention one thing yesterday. There is a high incidence of intermarriage here, which is why thalassemia is so common. It is also a cause of death in young children. There is no center or facility for thalassemia. These children need blood every fortnight or every month. Because there is no blood bank here, this is also the cause of their death.
+
+Follow-up question later: Are people moving between cities and cities to the villages, and if so, is it minimal or more or less the same as always?
+
+Answer: Yes, people are moving from one city to another but movement between cities is less than before. Movement between villages is same as before. The reduction in movement to cities is because of public transport being shut down.
+
+
+<p><section id="isso-thread">
+  <noscript>Javascript needs to be activated to view comments.</noscript>
+</section></p>
+

blog/2022/12/20/hacking-on-rose/.src/index.md

@@ -0,0 +1,37 @@
+Hacking on the Rose browser
+===========================
+
+I recently spent a few days hacking on the [rose browser](https://github.com/mini-rose/rose). It's a minimalist browser for Linux machines which is easy to play with. I enjoyed the experience, and thought to leave some notes.
+
+Rose is written in C, and uses the Webkit and GTK libraries. Webkit, which drives Safari, started out as a fork of some previous open-source libraries, [KHTML](https://en.wikipedia.org/wiki/KHTML) and [KJS](https://en.wikipedia.org/wiki/KJS_%28software%29). [GTK](https://en.wikipedia.org/wiki/GTK) is a library for creating graphical interfaces. You can use the two together using [WebKitGTK](https://webkitgtk.org/).
+
+![Image of this blogpost from the rose homepage](https://i.imgur.com/0sVCaN7.png)
+*<br>Pictured: An earlier version of this blogpost in the rose browser.*
+
+Personally, I find the simplicity of the code soothing. Still, to improve usability and for my own enjoyment, I've been adding some code to it. You can have a look at my tweaks [here](https://github.com/NunoSempere/rose-browser). These implement two main changes:
+
+1. I've implemented a [reader mode](https://github.com/NunoSempere/rose-browser/tree/personal/plugins/readability)
+2. I've added [redirection functionality](https://github.com/NunoSempere/rose-browser/tree/personal/plugins/libre_redirect), which redirects users to open source frontends of otherwise annoying websites.
+
+The reader mode, for instance, returns this beautiful to read page:
+
+![Pictured: Good newsletter, where you can read the content](https://i.imgur.com/ExEoWqq.png)
+
+when fed the cluttered aesthetic abomination that is Matt Levine's newsletter:
+
+![Pictured: Bad newsletter, with lots of advertisements](https://i.imgur.com/uRDsnXB.png)
+
+I lifted the code for doing this from [Firefox](https://github.com/mozilla/readability), figured out how to integrate it with WebKit, and then made a few modifications.
+
+As mentioned, I also wrote a version of [LibRedirect](https://libredirect.codeberg.page/) for the rose browser. It which direct annoying websites into better open-source versions:
+
+![Pictured: list of sites that I am redirecting](https://i.imgur.com/NRo9wrF.png)
+
+Lastly, I've added some code for installing the Rose browser on [Ubuntu 20.04](https://github.com/NunoSempere/rose-browser/raw/personal/rose), which is what I'm personally using. 
+
+If you are a close friend using Linux feel free to reach out if you get stuck trying to install this.
+
+
+<p><section id="isso-thread">
+  <noscript>Javascript needs to be activated to view comments.</noscript>
+</section></p>

blog/2022/12/20/hacking-on-rose/.src/index_gpt.md

@@ -0,0 +1,34 @@
+Hacking on the Rose browser
+===========================
+
+I recently had the pleasure of tinkering with the [rose browser](https://github.com/mini-rose/rose) for a few days. It's a Linux-based minimalist web browser, making it easy and fun to customize. To help others who may explore this project, I decided to leave some notes about my experience.
+
+Rose is written in C and takes advantage of the WebKit and GTK libraries. WebKit, which drives Safari, is a fork of the open-source KHTML and KJS libraries. GTK, on the other hand, is a library for enabling graphical user interfaces. You can utilize both libraries simultaneously by using WebKitGTK.
+
+Personally, I have found solace in the simplicity of this code. Nevertheless, for usability purposes and for my own enjoyment, I have been adding some code to it. You can have a look at my edits [here](https://github.com/NunoSempere/rose-browser).
+
+I've made two main changes to the [Rose Browser](https://github.com/NunoSempere/rose-browser): 
+
+1. I've implemented a [reader mode](https://github.com/NunoSempere/rose-browser/tree/personal/plugins/readability) 
+2. I've added [redirection functionality](https://github.com/NunoSempere/rose-browser/tree/personal/plugins/libre_redirect), which redirects users to open source frontends of otherwise annoying websites.
+
+The reader mode allows readers to access a page in a more visually-appealing way; it returns a page that is easy and enjoyable to read.
+
+
+Check out this [picture](https://i.imgur.com/ExEoWqq.png) of a great newsletter, where you can read its content.
+
+When presented with the unpleasant experience of reading Matt Levine's newsletter:
+
+
+
+![An image of an overcrowded newsletter full of advertisements](https://i.imgur.com/uRDsnXB.png)
+
+I obtained the code for this from [Firefox](https://github.com/mozilla/readability). Subsequently, I implemented it within WebKit and made a few modifications.
+
+I offer an alternative version of [LibRedirect](https://libredirect.codeberg.page/), which redirects annoying webpages to better, open-source alternatives.
+
+![List of sites to which I have redirected traffic](https://i.imgur.com/NRo9wrF.png)
+
+I have added instructions for installing the Rose browser on [Ubuntu 20.04](https://github.com/NunoSempere/rose-browser/raw/personal/rose), which is the version I am currently using.
+
+If you are a dear friend who is using Linux, please reach out for assistance if you run into any difficulties while attempting to install this.

blog/2022/12/20/hacking-on-rose/index.md

@@ -0,0 +1,32 @@
+Hacking on rose
+===============
+
+The [rose browser](https://github.com/mini-rose/rose) is a minimal browser for Linux machines. I've immensely enjoyed hacking on it this last week, so I thought I'd leave some notes.
+
+Rose is written in C, and it's based on Webkit and GTK. Webkit is the engine that drives Safari, and a fork of some previous open-source libraries, [KHTML](https://en.wikipedia.org/wiki/KHTML) and [KJS](https://en.wikipedia.org/wiki/KJS_%28software%29). [GTK](https://en.wikipedia.org/wiki/GTK) is a library for creating graphical interfaces. You can conveniently use the two together using [WebKitGTK](https://webkitgtk.org/).
+
+![Image of this blogpost from the rose homepage](https://i.imgur.com/0sVCaN7.png)
+*<br>Pictured: An earlier version of this blogpost in the rose browser.*
+
+Personally, I find the simplicity of the code soothing. At the same time, though, I've been adding some code to it, to make the browser more usable and for the fun of it. You can see my tweaks [here](https://github.com/NunoSempere/rose-browser).
+
+My first tweak was to add a [reader mode](https://github.com/NunoSempere/rose-browser/tree/personal/plugins/readability). It, for instance, returns this beautiful page:
+
+![Pictured: Good newsletter, where you can read the content](https://i.imgur.com/ExEoWqq.png)
+
+when fed the aesthetic abomination that is Matt Levine's newsletter:
+
+![Pictured: Bad newsletter, with lots of advertisements](https://i.imgur.com/uRDsnXB.png)
+
+I lifted the code for doing this from [Firefox](https://github.com/mozilla/readability), figured out how to integrate it with WebKit, and then improved it a bit.
+
+My second big tweak was to add [redirection functionality](https://github.com/NunoSempere/rose-browser/tree/personal/plugins/libre_redirect) from annoying websites to their open source frontends, in the style of [LibRedirect](https://libredirect.codeberg.page/):
+
+![Pictured: list of sites that I am redirecting](https://i.imgur.com/NRo9wrF.png)
+
+And I've added some code for installing this browser on [Ubuntu 20.04](https://github.com/NunoSempere/rose-browser/raw/personal/rose), which is what I'm personally using. If you are a dear friend using Linux feel free to ask for help if you get stuck trying to install this.
+
+<p><section id="isso-thread">
+  <noscript>Javascript needs to be activated to view comments.</noscript>
+</section></p>
+

blog/2022/12/23/ai-risk-rohin-shah/index.md

@@ -0,0 +1,43 @@
+A basic argument for AI risk
+============================
+
+Rohin Shah [writes](https://www.lesswrong.com/posts/bkpZHXMJx3dG5waA7/ways-to-buy-time?commentId=jropYhtAW72zfHRBr) (referenced [here](https://forum.effectivealtruism.org/posts/2S3CHPwaJBE5h8umW/read-the-sequences)):
+
+> Currently, I'd estimate there are ~50 people in the world who could make a case for working on AI alignment to me that I'd think wasn't clearly flawed. (I actually ran this experiment with ~20 people recently, 1 person succeeded. EDIT: I looked back and explicitly counted -- I ran it with at least 19 people, and 2 succeeded: one gave an argument for "AI risk is non-trivially likely", another gave an argument for "this is a speculative worry but worth investigating" which I wasn't previously counting but does meet my criterion above.)
+
+I thought this was surprising, so here is an attempt, time-capped at 45 mins.
+
+### 1. The concern is valid in the limit: An entity of arbitrary, God-like intelligence would be very scary.
+
+An entity of arbitrary, God-like intelligence would be very scary. We already see that the most intelligent humans, like von Neumann and the other Hungarian Martians, were able to perform feats of science that steered humanity's fate.
+
+If we had an artificial system that was as intelligent as von Neumann, this would be very scary, because it might be able to perform similar feats of science and engineering. Also, Moore's law is uncertain, but it seems likely that in a generation we could go from having just one artificial von Neuman to having many of it. This increases the stakes.
+
+### 2. Year and year we are approaching the limit: What comes after Comprehensive AI Systems?
+
+We can think about how the world would look like in 2030-2035 if many tasks are delegated to successors of GPT-3. In this world, interfaces between many services and AI systems exist, and these are used to affect real-world systems. For example, I might routinely use GPT-3 to edit my texts, translations might be performed in real time through speech recognition, or [automatic threat detection](https://www.lesswrong.com/posts/vDvKWdCCNo9moNcMr/us-military-global-information-dominance-experiments) and deployment might be used by the world's military.
+
+Then we can think about, well, how does the world look like the decade after that one, and the decade after, and so forth. And it looks like ML systems generally acquiring more and resposability around managing human systems.
+
+And in general, we might worry that as current systems become more and more capable, they might eventually exceed humans and start to manifest some of the dangers that a being of God-like intelligence would also display. Crucially, we think that the human brain is made out of human atoms and so in principle replicatable in silico. 
+
+### 3. Alignment proposals are uncertain, shaky and untested
+
+In this situation, we would love to have some mathematical proof that these AI systems which might end up making important decisions are, in some sense, friendly to humans. We don't have that guarantee. We might hope that there might be a strong incentive to create systems that increase human flourishing rather than reduce it. 
+
+But on the other hand, if we look at e.g., the algorithms driving social media and reducing attention spans, this doesn't really inspire much confidence. We can also look at the organizing structure of society and notice that it alredy falls prey to Goodhart's law in that maximizing profit does not maximize flourishing. Some examples might be the [Sumangali system](https://en.wikipedia.org/wiki/Sumangali_%28child_labour%29), Nestlé [stealing water to bottle in a drought](https://www.theguardian.com/us-news/2021/apr/27/california-nestle-water-san-bernardino-forest-drought), or lobbying from weapon manufacturers making war more likely. We might worry that similar dynamics might exist if more and more decisions are put in the hands of AI systems and these are programmed to maximize something that at first looks like human flourishing but ultimately doesn't.
+
+We could also worry about more speculative failure modes, in which very intelligent systems at first appear to be helpful but then stop being so as they become harder to stop. We see that these kinds of things happen with [reward hacking](https://docs.google.com/spreadsheets/d/e/2PACX-1vRPiprOaC3HsCf5Tuum8bRfzYUiKLRqJmbOoC-32JorNdfyTiRRsR7Ea5eWtvsWzuxo8bjOxCG84dAg/pubhtml) in curent models, and pop up in [models of very intelligent systems](https://www.lesswrong.com/posts/nyCHnY7T5PHPLjxmN/open-question-are-minimal-circuits-daemon-free). 
+
+### 4. Expected value calculations lead the way
+
+Because we expect these systems to be tightly integrated with the human economy, we would like to have guarantees. But we don't have them. Given that we don't have guarantees that bad outcomes won't happen, they might in fact happen. This would be bad.
+
+If we multiply the number of people who we would expect to be affected by future AI systems, this would be a large number. This is similar to how e.g., the US Federal Reserve sets monetary policy in the US, and so improving its decisions would reverberate across the US. But because AI systems will have a large scale impact, steering that impact would also be valuable. If we multiply out that impact (e.g., [here](https://www.beguide.org/hostile-artificial-intelligence.html)), the expected value turns out to be higher than other oportunities.
+
+
+---
+
+<p><section id="isso-thread">
+  <noscript>Javascript needs to be activated to view comments.</noscript>
+</section></p>

blog/2023/01/03/me-in-2022/index.md

@@ -0,0 +1,85 @@
+Me in 2022
+==========
+
+![](https://i.imgur.com/m5rQtBI.gif)
+
+The above *.gif* shows a snapshot taken by my computer at 12:00 for a large number of days of the year. The below *.gif* shows a snapshot taken by my computer every five minutes on the 22/02/2022:
+
+![](https://i.imgur.com/Pw1iMSn.gif)
+
+### To create such a *.gif* in Linux
+
+**a. Create a script to take a photo from your webcam:**
+
+```
+## Defs
+panopticonDir="~/.panopticon"
+
+selfiesDir="$panopticonDir/selfies"
+today="$(date +"%Y%m%d")"
+timeNow="$(date +"%H%M%S")"
+
+## Init
+mkdir -p "$selfiesDir/$today"
+
+## Selfies
+
+selfieFileName="webcam_$timeNow.jpg"
+/usr/bin/fswebcam -r 1280x720 "$selfiesDir/$today/$selfieFileName" 
+# ^ works with pipewire
+
+```
+
+**b. Call the script from within crontab**
+
+Call 
+
+```
+$ sudo crontab -e
+```
+
+and then paste:
+
+```
+*/5 * * * * /home/loki/.panopticon/shoot.sh
+```
+
+**c. Put it all together into a gif**
+
+One gif from snapshots taken at 12:00.
+
+```
+summary_dir="~/.panopticon/summary-12"
+mkdir summary_dir
+for dir in ~/.panopticon/*/ ; do
+  if [[ -d "$dir" && ! -L "$dir" ]]; then
+    echo "Entering $dir";
+    dirname_raw="$(echo "$dir" | sed 's#/##')"
+    temp_photo_name="$(echo $dirname_raw/webcam_1200*)"
+    echo "$temp_photo_name"
+    cp $temp_photo_name temp.jpg
+    mv temp.jpg $summary_dir/$dirname_raw.jpg
+  fi;
+done
+
+convert -delay 10 -loop 0 $summary_dir/*.jpg 12.gif
+
+```
+
+One for each day with something like:
+
+```
+for dir in */ ; do
+  if [[ -d "$dir" && ! -L "$dir" ]]; then
+    echo "Entering $dir";
+    dirname_raw="$(echo "$dir" | sed 's#/##')"
+    convert -delay 10 -loop 0 $dirname_raw/*.jpg daily-gifs/$dirname_raw.gif
+    echo "Created daily_gifs/$dirname_raw"
+  fi;
+done
+
+```
+
+<p><section id="isso-thread">
+  <noscript>Javascript needs to be activated to view comments.</noscript>
+</section></p>

blog/2023/01/07/forecasting-newsletter-november-december-2022/.src/index.html

@@ -0,0 +1,169 @@
+<h2>Highlights</h2>
+<ul>
+<li>PredictIt nears its <a href="https://insightprediction.com/m/18505/will-predictit-survive" target="_blank" rel="noopener">probable demise</a></li>
+<li>American Civics Exchange offers <a href="https://otc.amciv.com/" target="_blank" rel="noopener">political betting</a> to Americans using weird legal loophole</li>
+<li>Forecasting community member Avraham Eisenberg <a href="https://www.coindesk.com/policy/2022/12/27/mango-markets-exploiter-eisenberg-arrested-in-puerto-rico/" target="_blank" rel="noopener">arrested for $100M+ theft</a> (<a href="https://web.archive.org/web/20230106173959/https://www.coindesk.com/policy/2022/12/27/mango-markets-exploiter-eisenberg-arrested-in-puerto-rico/" target="_blank" rel="noopener">a</a>).</li>
+<li>Forecasting Research Institute <a href="https://ea.greaterwrong.com/posts/kEd5qWwg8pZjWAeFS/announcing-the-forecasting-research-institute-we-re-hiring" target="_blank" rel="noopener">launches publicly</a></li>
+<li>Blogpost <a href="https://www.metacausal.com/givewells-uncertainty-problem/" target="_blank" rel="noopener">suggests that GiveWell use uncertainty</a>, wins $20k</li>
+<li>Contrarian <a href="https://www.metacausal.com/givewells-uncertainty-problem/" target="_blank" rel="noopener">offers $500k bet</a>, then chickens out</li>
+<li>Walter Frick writes a <a href="https://www.niemanlab.org/2022/12/journalists-wake-up-to-the-power-of-prediction-markets/" target="_blank" rel="noopener">resource to introduce journalists to prediction markets</a></li>
+<li>Yearly feedback form</li>
+</ul>
+<h2>Index</h2>
+<ul>
+<li>Prediction Markets and Forecasting Platforms</li>
+<ul>
+<li>PredictIt</li>
+<li>American Civics Exchange</li>
+<li>Polymarket</li>
+<li>Insight Prediction</li>
+<li>Kalshi</li>
+<li>INFER</li>
+<li>Metaculus</li>
+<li>Manifold</li>
+<li>Odds and Ends</li>
+</ul>
+<li>Opportunities</li>
+<li>Research</li>
+<ul>
+<li>Shortform</li>
+<li>Longform</li>
+</ul>
+<li>In the News</li>
+<li>Extra: The tax-evaded Nazi money which influences German politics and US/NATO relationships has opened a new forecasting platform.</li>
+<li>Yearly housekeeping</li>
+</ul>
+<p>Browse past newsletters <a href="https://forecasting.substack.com/" target="_blank" rel="noopener">here</a> (<a href="http://web.archive.org/web/20230105001738/https://forecasting.substack.com/" target="_blank" rel="noopener">a</a>), or view this newsletter on the EA forum here. If you have a content suggestion or want to reach out, you can leave a comment or find me on <a href="https://twitter.com/NunoSempere" target="_blank" rel="noopener">Twitter</a>.</p>
+<h2>Prediction Markets and Forecasting Platforms</h2>
+<h3>PredictIt</h3>
+<p>Racing against the clock, PredictIt is trying to get permission from the CFTC to continue existing. From PredictIt&rsquo;s newsletter:</p>
+<p>As you may know, the Commodity Futures Trading Commission (CFTC) decided in August to revoke the authorization that allowed PredictIt to operate <a href="https://www.predictit.org/platform-announcements" target="_blank" rel="noopener">effective Feb. 15, 2023</a> (<a href="http://web.archive.org/web/20221223063826/https://www.predictit.org/platform-announcements" target="_blank" rel="noopener">a</a>) (<a href="https://www.cftc.gov/PressRoom/PressReleases/8567-22" target="_blank" rel="noopener">original CFTC source</a> (<a href="http://web.archive.org/web/20221217222553/https://www.cftc.gov/PressRoom/PressReleases/8567-22" target="_blank" rel="noopener">a</a>)). More than a dozen of your fellow PredictIt traders, as well as academic data users and PredictIt&rsquo;s parent company Aristotle, have challenged this decision in federal court with the goal of keeping election markets open and operating past the CFTC&rsquo;s arbitrary Feb. 15, 2023, deadline.</p>
+<p>Given the time-sensitive nature of this fight, the <a href="https://www.casino.org/news/predictit-to-seek-cftc-injunction-in-appeals-court-after-lower-court-fails-to-act/" target="_blank" rel="noopener">plaintiffs filed a motion</a> (<a href="http://web.archive.org/web/20230103080014/https://www.casino.org/news/predictit-to-seek-cftc-injunction-in-appeals-court-after-lower-court-fails-to-act/" target="_blank" rel="noopener">a</a>) last week to move the case to the United States Court of Appeals for the Fifth Circuit, which is the quickest path towards attaining justice for our traders and academic partners. We understand that legal battles do not generally make for exhilarating newsletter content, but as valued members of our community, we want you to know that we&rsquo;re fighting on every available battlefield for the future of PredictIt and political prediction markets.</p>
+<p>To that end, Aristotle, has also applied to the CFTC for permission to operate a Designated Contract Market (DCM), which will offer event contracts that include certain political outcomes. We&rsquo;re well along in that process and hope to have approval in the coming months.</p>
+<p>If approved, PredictIt Exchange will list many of the same contracts that you love: polling averages, nominations, confirmations and legislative outcomes, among other topics.</p>
+<p>This next step toward becoming a regulated entity has been a long-time goal of the PredictIt team. We&rsquo;ll be in touch soon with more information about how to sign up for PredictIt Exchange and other exciting developments in the works for next year. Stay tuned!</p>
+<h3>American Civics Exchange</h3>
+<p>The newly created American Civics Exchange is offering <a href="https://otc.amciv.com/dashboard" target="_blank" rel="noopener">over-the-counter betting</a> (<a href="http://web.archive.org/web/20221122165636/https://otc.amciv.com/dashboard" target="_blank" rel="noopener">a</a>) on political events.</p>
+<p>I'm not clear on how <a href="https://en.wikipedia.org/wiki/Over-the-counter_%28finance%29" target="_blank" rel="noopener">this is legal</a> (<a href="https://web.archive.org/web/20230106180304/https://en.wikipedia.org/wiki/Over-the-counter_%28finance%29" target="_blank" rel="noopener">a</a>), but readers might consult their "What is ACE otc's regulatory framework?" section in their <a href="https://otc.amciv.com/page/faq" target="_blank" rel="noopener">FAQ</a> (<a href="http://web.archive.org/web/20230105001904/https://otc.amciv.com/page/faq" target="_blank" rel="noopener">a</a>). The man behind the thing is <a href="https://twitter.com/FlipPidot" target="_blank" rel="noopener">Filip Pidot</a> (<a href="https://web.archive.org/web/20230106192455/https://twitter.com/FlipPidot" target="_blank" rel="noopener">a</a>), who previously ran the <a href="https://www.youtube.com/@OldBullTV/videos" target="_blank" rel="noopener">Old Bull TV</a> (<a href="http://web.archive.org/web/20230105002037/https://www.youtube.com/@OldBullTV/videos" target="_blank" rel="noopener">a</a>) youtube channel, and is generally considered a respectable community member.</p>
+<h3>Polymarket</h3>
+<p>Polymarket deploys an <a href="https://github.com/Polymarket/uma-ctf-adapter" target="_blank" rel="noopener">adapter</a> (<a href="http://web.archive.org/web/20221013234314/https://github.com/Polymarket/uma-ctf-adapter" target="_blank" rel="noopener">a</a>) between its Keynesian beauty contest resolution mechanism, <a href="https://umaproject.org/" target="_blank" rel="noopener">UMA</a> (<a href="http://web.archive.org/web/20230104180400/https://umaproject.org/" target="_blank" rel="noopener">a</a>), and actual resolutions. There is an "emergencyResolve" feature, which judging by the name could be used to override or bypass the UMA resolution. This is marginally concerning, because it could be used to siphon money away from markets, by betting on the less likely outcome and then resolving to it.</p>
+<p>Ultimately, I don't think this matters very much, because if Polymarket was compromised, users' wallets could probably be drained through some change in the webpage. Still, this downgrades UMA from its previous status as a source of truth to merely a convenient resolution mechanism,</p>
+<h3>Insight Prediction</h3>
+<p>Insight Prediction <a href="https://twitter.com/Insight_Predict/status/1587428761456193536" target="_blank" rel="noopener">introduced</a> (<a href="http://web.archive.org/web/20230105001841/https://twitter.com/Insight_Predict/status/1587428761456193536" target="_blank" rel="noopener">a</a>) some innovations around "sudden death markets". It's difficult to do market-making for markets about discrete events, because if the event happens, traders will quickly make bets and rake in profit before the market-maker notices. And so:</p>
+<p>&hellip;what we've implemented is the ability to have markets where we return all bets after a particular event has transpired. Bets placed before the event will be honored, while bets placed after will be returned. This of course requires bets in the market to be locked (72 hours)</p>
+<p>You can see this functionality in this market: <a href="https://insightprediction.com/m/67960/will-elon-musk-father-another-child-by-august-2023" target="_blank" rel="noopener">Will Elon Musk Father Another Child Before August 2023?</a> (<a href="http://web.archive.org/web/20230105001846/https://insightprediction.com/m/67960/will-elon-musk-father-another-child-by-august-2023" target="_blank" rel="noopener">a</a>) market.</p>
+<h3>Kalshi</h3>
+<p>Kalshi <a href="https://kalshi.com/blog/apiv2-is-here/" target="_blank" rel="noopener">updates their API</a> (<a href="https://web.archive.org/web/20230106192534/https://kalshi.com/blog/apiv2-is-here/" target="_blank" rel="noopener">a</a>) and, separately, gets <a href="https://news.ycombinator.com/item?id=33696486" target="_blank" rel="noopener">lampooned in Hacker News</a> (<a href="https://web.archive.org/web/20230106174123/https://news.ycombinator.com/item?id=33696486" target="_blank" rel="noopener">a</a>):</p>
+<p>That's neat but how does one hedge a $800k loan with a max position of $25k? Idea seems spurious. The difference is substantially higher. Compare a pre-hike 2.8% with a present 6.8%. Your $25k hedge is going to be pointless.</p>
+<p>Before Kalshi, markets that allowed you to trade on economically relevant events were illegal or unregulated.</p>
+<p>Totally untrue. PredictIt was legal and regulated and well-loved for many years, operating with the permission of the CFTC under a no-action letter. Then Kalshi hired former CFTC commissioner Brian Quintenz and soon, PredictIt was suddenly deemed by the CFTC to have committed still-unenumerated violations of the no-action letter.</p>
+<p>This is a rotten way to do business and shame on YC for being involved in it.</p>
+<h3>INFER</h3>
+<p>INFER has a few <a href="https://www.infer-pub.com/archive" target="_blank" rel="noopener">quarterly reports</a> (<a href="http://web.archive.org/web/20230105002053/https://www.infer-pub.com/archive" target="_blank" rel="noopener">a</a>) on their forecasts on Synthetic Biology, AI and Microelectronics. It also has a <a href="https://www.infer-pub.com/future-bowl-tournament" target="_blank" rel="noopener">$5.25k</a> (<a href="http://web.archive.org/web/20230105002109/https://www.infer-pub.com/future-bowl-tournament" target="_blank" rel="noopener">a</a>) tournament.</p>
+<p>When Metaculus got a <a href="https://www.openphilanthropy.org/grants/metaculus-platform-development/" target="_blank" rel="noopener">$5.5M grant</a> (<a href="http://web.archive.org/web/20230105002123/https://www.openphilanthropy.org/grants/metaculus-platform-development/" target="_blank" rel="noopener">a</a>) earlier this year, I could mostly see this reverberating, them hiring more people, a few teams being created, people I was keeping tabs on getting hired, more forecasting contests happening, and so on. You know, $5M is a small fortune, and I try to listen to the pulse of these things. Manifold Markets got built on top of $1M.</p>
+<p>So for a while now, it has been very unclear to me where the <a href="https://www.openphilanthropy.org/grants/applied-research-laboratory-for-intelligence-and-security-forecasting-platforms/" target="_blank" rel="noopener">$8M that INFER's parent organization got from Open Philanthropy</a> (<a href="http://web.archive.org/web/20230105002137/https://www.openphilanthropy.org/grants/applied-research-laboratory-for-intelligence-and-security-forecasting-platforms/" target="_blank" rel="noopener">a</a>) was going. Things just weren't very visibly different from what I would expect to see if that grant hadn't really happened. INFER's forecasting rewards continued to be pretty small.</p>
+<p>Taking a page from <a href="https://statmodeling.stat.columbia.edu/" target="_blank" rel="noopener">Andrew Gelman</a> (<a href="http://web.archive.org/web/20230101023816/https://statmodeling.stat.columbia.edu/" target="_blank" rel="noopener">a</a>), who is extremely meek when pointing these kinds of issues out, there could be many explanations. For example, it's possible that it does add up, that infrastructure and putting these kinds of reports out does take that much money. Or that they are spending the money slowly and sustainably for the long term. Or that the University of Maryland administration takes a really large chunk of funds. I am also assuming that the $8M in two years for two platforms doesn't correspond to something in the very rough neighbourhood of $2M per year per platform, but it could be that that's not the case. It's also possible that the INFER forecasting sphere and the sphere that I pay the most attention to don't overlap as much, which could be a positive. Still, the difference between the funds they receive and the impact that I perceive as for a while a small mystery to me.</p>
+<p>Now, in its yearly review, INFER <a href="https://www.infer-pub.com/the-pub/season-review-2022" target="_blank" rel="noopener">mentions</a> (<a href="http://web.archive.org/web/20221222200606/https://www.infer-pub.com/the-pub/season-review-2022" target="_blank" rel="noopener">a</a>) working on "an internal U.S. Government-wide site" for 2023. That does seem like it could absorb large amounts of funds. Still, personally, I'd love to see a bill of how much was spent where.</p>
+<h3>Metaculus</h3>
+<p>Metaculus held a <a href="https://scribe.froth.zone/announcing-metaculuss-million-predictions-hackathon-91c2dfa3f39" target="_blank" rel="noopener">Million Predictions Hackathon</a> (<a href="https://web.archive.org/web/20230106174232/https://scribe.froth.zone/announcing-metaculuss-million-predictions-hackathon-91c2dfa3f39" target="_blank" rel="noopener">a</a>), and posted their <a href="https://scribe.froth.zone/metaculus-year-in-review-2022-c92ff9cd87a0" target="_blank" rel="noopener">year in review</a> (<a href="https://web.archive.org/web/20230106174302/https://scribe.froth.zone/metaculus-year-in-review-2022-c92ff9cd87a0" target="_blank" rel="noopener">a</a>). They are also hosting a <a href="https://www.metaculus.com/tournament/beginner-tournament/" target="_blank" rel="noopener">beginner tournament</a> (<a href="http://web.archive.org/web/20221120092344/https://www.metaculus.com/tournament/beginner-tournament/" target="_blank" rel="noopener">a</a>), which seems like a neat way of introduction to forecasting.</p>
+<h3>Manifold</h3>
+<p>Vincent Luczkow <a href="https://github.com/vluzko/manifoldpy" target="_blank" rel="noopener">analyzes</a> (<a href="http://web.archive.org/web/20221228201434/https://github.com/vluzko/manifoldpy" target="_blank" rel="noopener">a</a>) whether Manifold Markets are well calibrated, and finds that they are:</p>
+<p>A Manifold Community member analyzed the performance of various prediction platforms on the <a href="https://firstsigma.substack.com/p/midterm-elections-forecast-comparison" target="_blank" rel="noopener">US elections</a> (<a href="http://web.archive.org/web/20221215030200/https://firstsigma.substack.com/p/midterm-elections-forecast-comparison" target="_blank" rel="noopener">a</a>). I find that these analyses don't really take into account that political outcomes are massively correlated. And so in years in which Democrats do well, platforms with a Democratic bias will do well, and vice-versa. Still, this isn't totally uninformative.</p>
+<p>Manifold adds swipe functionality to bet. I think this is pure evil genius, in the sense of being a very addictive skinner box, and I'm very impressed. You can try it <a href="https://manifold.markets/swipe" target="_blank" rel="noopener">here</a> (<a href="http://web.archive.org/web/20221031121657/https://manifold.markets/swipe" target="_blank" rel="noopener">a</a>).</p>
+<p>Manifold now has <a href="https://play.google.com/store/apps/details?id=com.markets.manifoldhttps://play.google.com/store/apps/details?id=com.markets.manifold&amp;pli=1" target="_blank" rel="noopener">Android</a> (<a href="https://web.archive.org/web/20230106174337/https://play.google.com/store/apps/details?id=com.markets.manifoldhttps://play.google.com/store/apps/details?id=com.markets.manifold&amp;pli=1" target="_blank" rel="noopener">a</a>) and <a href="https://apps.apple.com/us/app/manifold-markets/id6444136749" target="_blank" rel="noopener">iOS</a> (<a href="http://web.archive.org/web/20221208084400/https://apps.apple.com/us/app/manifold-markets/id6444136749" target="_blank" rel="noopener">a</a>) apps.</p>
+<h3>Odds and ends</h3>
+<p>The FTX Foundation, a major founder of innovative forecasting projects, exists no longer after the downfall of FTX. More on this in the next edition of this newsletter.</p>
+<p>The Effective Altruism Forum has started a <a href="https://forum.effectivealtruism.org/posts/azL6uPcbCqBfJ37TJ/announcing-a-subforum-for-forecasting-and-estimation" target="_blank" rel="noopener">subforum for forecasting and estimation</a> (<a href="https://web.archive.org/web/20230104122631/https://forum.effectivealtruism.org/posts/azL6uPcbCqBfJ37TJ/announcing-a-subforum-for-forecasting-and-estimation" target="_blank" rel="noopener">a</a>). Right now it mostly has some seed discussions started by employees of the Center for Effective Altruism.&nbsp;</p>
+<p>I don't recommend that subforum for general forecasting discussion because I think that the EA Forum has too onerous "be nice" rules, whereas I tend to most like spaces that are maximally uncensorious and are willing to sacrifice other values in the pursuit of accuracy. For instance, Discord spaces from Metaculus, Polymarket &amp; others have tended to be extremely unmoderated.&nbsp;</p>
+<p>Some comments from Good Judgment Open from the last long while:</p>
+<ul>
+<li><a href="https://www.gjopen.com/comments/1545611" target="_blank" rel="noopener">julick</a> (<a href="https://web.archive.org/web/20230106174359/https://www.gjopen.com/comments/1545611" target="_blank" rel="noopener">a</a>) summarizes some <a href="https://www.cambridge.org/core/journals/american-political-science-review/article/abs/war-and-the-fate-of-regimes-a-comparative-analysis/88056B8C9BE0413DB349086653B58520" target="_blank" rel="noopener">Cambridge research on regime change</a> (<a href="http://web.archive.org/web/20220914032710/https://www.cambridge.org/core/journals/american-political-science-review/article/abs/war-and-the-fate-of-regimes-a-comparative-analysis/88056B8C9BE0413DB349086653B58520" target="_blank" rel="noopener">a</a>) and points out that "For regimes that initiated wars and lost them the regime change by violence within 3 years is 60-80%. For an initiator that won the probability is 20-35%."</li>
+<li><a href="https://www.gjopen.com/comments/1554036" target="_blank" rel="noopener">Anneinak</a> (<a href="https://web.archive.org/web/20230106174419/https://www.gjopen.com/comments/1554036" target="_blank" rel="noopener">a</a>) gives a 15% to Twitter crashing by December 2023, and points to <a href="https://www.gjopen.com/comments/1554036" target="_blank" rel="noopener">this article</a> (<a href="https://web.archive.org/web/20230106174419/https://www.gjopen.com/comments/1554036" target="_blank" rel="noopener">a</a>): "If the [EU] Commission elects to designate Twitter a VLOP [Very Large Online Platform] under the DSA [Digital Services Act] the business will face an accelerated compliance timetable with oversight kicking in in February next year &mdash; rather than in February 2024 &mdash; and with a tougher set of requirements to assess and mitigate risks on its platform."</li>
+<li>Some <a href="https://www.gjopen.com/questions/2659-between-9-december-2022-and-9-june-2023-will-north-korea-detonate-a-nuclear-device" target="_blank" rel="noopener">interesting discussion</a> (<a href="https://web.archive.org/web/20230106174450/https://www.gjopen.com/questions/2659-between-9-december-2022-and-9-june-2023-will-north-korea-detonate-a-nuclear-device" target="_blank" rel="noopener">a</a>) on whether North Korea will detonate a nuclear device, which includes and would most likely be a nuclear test.</li>
+<li>Forecaster <a href="https://www.gjopen.com/comments/1568206" target="_blank" rel="noopener">belikewater</a> (<a href="https://web.archive.org/web/20230106174513/https://www.gjopen.com/comments/1568206" target="_blank" rel="noopener">a</a>) does a nice, textbook base rate calculation to conclude that the current Italian Prime Minister, Meloni, will probably not (10%) stop being PM by October 2023.</li>
+</ul>
+<p>A decentralized sports prediction market has gotten <a href="https://www.theblock.co/post/194496/susquehanna-bets-on-decentralized-sports-prediction-market-frontrunner" target="_blank" rel="noopener">circa $5M</a> (<a href="https://web.archive.org/web/20230106174536/https://www.theblock.co/post/194496/susquehanna-bets-on-decentralized-sports-prediction-market-frontrunner" target="_blank" rel="noopener">a</a>) in <a href="https://techfundingnews.com/frontrunner-secures-4-75m-to-create-decentralised-sports-prediction-market/" target="_blank" rel="noopener">funding</a> (<a href="http://web.archive.org/web/20221224043943/https://techfundingnews.com/frontrunner-secures-4-75m-to-create-decentralised-sports-prediction-market/" target="_blank" rel="noopener">a</a>).</p>
+<p>Hypermind continues to host its <a href="https://prod.hypermind.com/ngdp/en/showcase2/showcase.html?sc=RUSSANCT1" target="_blank" rel="noopener">Russia Punished</a> (<a href="https://web.archive.org/web/20230106174607/https://prod.hypermind.com/ngdp/en/showcase2/showcase.html?sc=RUSSANCT1" target="_blank" rel="noopener">a</a>) series of questions.</p>
+<p>Scott Alexander wrote a <a href="https://astralcodexten.substack.com/p/prediction-market-faq" target="_blank" rel="noopener">Prediction Market FAQ</a> (<a href="https://web.archive.org/web/20230106174747/https://astralcodexten.substack.com/p/prediction-market-faq" target="_blank" rel="noopener">a</a>) and is hosting a <a href="https://astralcodexten.substack.com/p/2023-prediction-contest" target="_blank" rel="noopener">prediction contest</a> (<a href="http://web.archive.org/web/20230103085602/https://astralcodexten.substack.com/p/2023-prediction-contest" target="_blank" rel="noopener">a</a>) with a few days left to enter. If someone calculates expected reward over expected time, please post it as a comment.</p>
+<p>Web3 betting platform <a href="https://newsbtc.com/news/company/dexsport-loses-400000-in-hack-user-funds-remain-unaffected/" target="_blank" rel="noopener">loses $0.4M in hack</a> (<a href="http://web.archive.org/web/20221211201410/https://newsbtc.com/news/company/dexsport-loses-400000-in-hack-user-funds-remain-unaffected/" target="_blank" rel="noopener">a</a>).</p>
+<p><a href="https://againsttheodds.es/" target="_blank" rel="noopener">Against the Odds</a> (<a href="http://web.archive.org/web/20230105125805/https://againsttheodds.es/" target="_blank" rel="noopener">a</a>) is a platform available to Spaniards which offers the opportunity to earn around $500/month through "crossed bets", i.e., betting one thing in one prediction market and the opposite in another, in order to make a guaranteed profit. The service itself seems legit and comes recommended by a friend. But interested Spaniards should calculate whether this is worth it, e.g,. earning 7&euro; for 5 mins of work is 84&euro;/hour, and in practice something like 50&euro;/hour including time to set up things.</p>
+<p>Forecasting community member Avraham Eisenberg was both despised and admired after pulling off a <a href="https://www.coindesk.com/business/2022/10/15/114m-mango-markets-exploiter-outs-himself-returns-most-of-the-money/" target="_blank" rel="noopener">$114M heist</a> (<a href="http://web.archive.org/web/20221223162406/https://www.coindesk.com/business/2022/10/15/114m-mango-markets-exploiter-outs-himself-returns-most-of-the-money/" target="_blank" rel="noopener">a</a>) on a prediction platform. Now, he has been <a href="https://www.coindesk.com/policy/2022/12/27/mango-markets-exploiter-eisenberg-arrested-in-puerto-rico/" target="_blank" rel="noopener">arrested in Puerto Rico</a> (<a href="https://web.archive.org/web/20230106173959/https://www.coindesk.com/policy/2022/12/27/mango-markets-exploiter-eisenberg-arrested-in-puerto-rico/" target="_blank" rel="noopener">a</a>), and will be facing trial. He remains 47th on the Metaculus leaderboard, as can be seen on <a href="https://www.metaculus.com/accounts/profile/114222/" target="_blank" rel="noopener">his profile</a> (<a href="http://web.archive.org/web/20221225212754/https://www.metaculus.com/accounts/profile/114222/" target="_blank" rel="noopener">a</a>).</p>
+<h2>Opportunities</h2>
+<p>The <a href="https://forecastingresearch.org/" target="_blank" rel="noopener">Forecasting Research Institute</a> (<a href="http://web.archive.org/web/20221222190557/https://forecastingresearch.org/" target="_blank" rel="noopener">a</a>) is a new think tank which has some senior research talent. Their <a href="https://forecastingresearch.org/research" target="_blank" rel="noopener">research page</a> (<a href="http://web.archive.org/web/20221214224323/https://forecastingresearch.org/research" target="_blank" rel="noopener">a</a>) should give readers a good taste of what they are about; my impression is that they have a strong academic component and will be aiming to be a bit more institutional than other efforts in the space. I hesitate to mention this, but Phil Tetlock takes the perhaps somewhat ceremonial or advisory role of President.</p>
+<p><a href="https://ea.greaterwrong.com/posts/kEd5qWwg8pZjWAeFS/announcing-the-forecasting-research-institute-we-re-hiring" target="_blank" rel="noopener">Here</a> (<a href="https://web.archive.org/web/20230106174029/https://ea.greaterwrong.com/posts/kEd5qWwg8pZjWAeFS/announcing-the-forecasting-research-institute-we-re-hiring" target="_blank" rel="noopener">a</a>) is a post on the EA forum introducing them. They are currently <a href="https://forecastingresearch.org/apply" target="_blank" rel="noopener">hiring</a> (<a href="http://web.archive.org/web/20221222190529/https://forecastingresearch.org/apply" target="_blank" rel="noopener">a</a>) for research analyst ($70k/year), data analyst ($70k), content editor ($60k) and research assistant ($15/hour) positions.</p>
+<p>Other people who are hiring are</p>
+<ul>
+<li><a href="https://apply.workable.com/metaculus/" target="_blank" rel="noopener">Metaculus</a> (<a href="http://web.archive.org/web/20221209055644/https://apply.workable.com/metaculus/" target="_blank" rel="noopener">a</a>)</li>
+<li><a href="https://statmodeling.stat.columbia.edu/2023/01/06/blue-rose-research-is-hiring/" target="_blank" rel="noopener">Blue Rose research</a> (<a href="http://web.archive.org/web/20230106074310/https://statmodeling.stat.columbia.edu/2023/01/06/blue-rose-research-is-hiring/" target="_blank" rel="noopener">a</a>)</li>
+<li>Insight Prediction <a href="https://www.econjobrumors.com/topic/insight-prediction-is-hiring" target="_blank" rel="noopener">was hiring</a> (<a href="https://web.archive.org/web/20230106174830/https://www.econjobrumors.com/topic/insight-prediction-is-hiring" target="_blank" rel="noopener">a</a>), and maybe still is</li>
+</ul>
+<h2>Writeups</h2>
+<h3>Shortform</h3>
+<p>The US 2022 congressional elections happened. Some relevant pieces on that:</p>
+<ul>
+<li>Arpit Gupta looks at the <a href="https://arpitrage.substack.com/p/loss-for-prediction-markets-in-the" target="_blank" rel="noopener">relative performance</a> (<a href="http://web.archive.org/web/20230105002406/https://arpitrage.substack.com/p/loss-for-prediction-markets-in-the" target="_blank" rel="noopener">a</a>) of PredictIt, 538, Manifold Markets and Metaculus in the 2022 US election. He concludes that Metaculus does best.&nbsp;</li>
+<li>This substack also <a href="https://mikesaintantoine.substack.com/p/scoring-midterm-election-forecasts" target="_blank" rel="noopener">compares PredictIt, 538 and Manifold Markets</a> (<a href="http://web.archive.org/web/20221126214755/https://mikesaintantoine.substack.com/p/scoring-midterm-election-forecasts" target="_blank" rel="noopener">a</a>).</li>
+<li>In postmortem analysis, FiveThrirtyEight <a href="https://fivethirtyeight.com/features/how-a-data-processing-error-changed-our-deluxe-forecast/" target="_blank" rel="noopener">finds that a data aggregation error meaningfully changed their forecasts</a> (<a href="http://web.archive.org/web/20221201012643/https://fivethirtyeight.com/features/how-a-data-processing-error-changed-our-deluxe-forecast/" target="_blank" rel="noopener">a</a>).</li>
+<li>Tanae Rao collects <a href="https://github.com/tanaerao/polymarket-midterms" target="_blank" rel="noopener">all trades on Polymarket for the 2022 US midterm elections</a> (<a href="http://web.archive.org/web/20221120230038/https://github.com/tanaerao/polymarket-midterms" target="_blank" rel="noopener">a</a>).</li>
+</ul>
+<p>With regard to comparisons between platforms, I don&rsquo;t think that those analyses are completely uninformative. But I'd be hesitant to draw conclusions from one electoral season, because election outcomes are correlated. So for instance it could be that PredictIt is biased in favour of Republicans, Metaculus is biased in favour of Democrats, and Democrats did better this time.&nbsp;</p>
+<p>In <a href="https://forum.effectivealtruism.org/posts/ytHCpLbT6A4gxqH8s/tracking-the-money-flows-in-forecasting" target="_blank" rel="noopener">Tracking the money flows in forecasting</a> (<a href="http://web.archive.org/web/20230105002212/https://forum.effectivealtruism.org/posts/ytHCpLbT6A4gxqH8s/tracking-the-money-flows-in-forecasting" target="_blank" rel="noopener">a</a>), I post some rough monetary valuation estimates for a large number of forecasting or prediction market organizations. The most out-of-place platform there is INFER, as reviewed above.</p>
+<p><a href="https://csustan.csustan.edu/~tom/Lecture-Notes/Non-Ergodic/Non-Ergodic-Short/Non-Ergodic-Short.pdf" target="_blank" rel="noopener">This online presentation</a> (<a href="http://web.archive.org/web/20221115165242/https://csustan.csustan.edu/~tom/Lecture-Notes/Non-Ergodic/Non-Ergodic-Short/Non-Ergodic-Short.pdf" target="_blank" rel="noopener">a</a>) gives a few examples of systems whose expected value is far apart from the most likely value. h/t <a href="https://twitter.com/AdamMarblestone" target="_blank" rel="noopener">Adam Marblestone</a> (<a href="https://web.archive.org/web/20221206194732/https://twitter.com/AdamMarblestone" target="_blank" rel="noopener">a</a>).</p>
+<p>Gelman <a href="https://statmodeling.stat.columbia.edu/2022/11/12/history-of-time-series-forecasting-competitions/" target="_blank" rel="noopener">points to a history of forecasting competitions</a> (<a href="https://web.archive.org/web/20221127082244/https://statmodeling.stat.columbia.edu/2022/11/12/history-of-time-series-forecasting-competitions/" target="_blank" rel="noopener">a</a>).</p>
+<p>Jaime Sevilla posts <a href="https://forum.effectivealtruism.org/posts/ozPL3mLGShqvjhiaG/some-research-ideas-in-forecasting" target="_blank" rel="noopener">Some research ideas in forecasting</a> (<a href="https://web.archive.org/web/20230105002420/https://forum.effectivealtruism.org/posts/ozPL3mLGShqvjhiaG/some-research-ideas-in-forecasting" target="_blank" rel="noopener">a</a>).</p>
+<p>The great Robin Hanson proposes <a href="https://www.overcomingbias.com/2022/11/clean-politician-bonds.html" target="_blank" rel="noopener">clean politician bonds</a> (<a href="https://web.archive.org/web/20221224124910/https://www.overcomingbias.com/2022/11/clean-politician-bonds.html" target="_blank" rel="noopener">a</a>):</p>
+<p>Assume you will vote for 1 of 2 candidates for US Mayor, Governor, or House of Repr. Only 1 has posted $1M bond payable to anyone who proves their misbehavior re lies, bribes, or other cheating. On average, what is chance you vote for this candidate?</p>
+<p><a href="https://breakingthemarket.com/the-most-misunderstood-force-in-the-universe/" target="_blank" rel="noopener">This brief blogpost</a> (<a href="http://web.archive.org/web/20221117115030/https://breakingthemarket.com/the-most-misunderstood-force-in-the-universe/" target="_blank" rel="noopener">a</a>) looks at when the geometric average of returns is a misleading indicator.</p>
+<p>Alvaro de Menard writes <a href="https://fantasticanachronism.com/2022/11/21/forecasting-forecasting/" target="_blank" rel="noopener">Forecasting Forecasting</a> (<a href="http://web.archive.org/web/20221215042936/https://fantasticanachronism.com/2022/11/21/forecasting-forecasting/" target="_blank" rel="noopener">a</a>), a short article looking at his perspective on the future of forecasting. Curiously, the article is fairly obsequious towards my forecasting group, Samotsvety.</p>
+<p>There is an AI risk tournament whose results should be coming up soon that had superforecasters look at the chance of existential risk tournament due to AI. Participant Ege Erdil <a href="https://twitter.com/EgeErdil2/status/1594723484860665858" target="_blank" rel="noopener">writes</a> (<a href="https://web.archive.org/web/20230106175129/https://twitter.com/EgeErdil2/status/1594723484860665858" target="_blank" rel="noopener">a</a>):</p>
+<p>i was one of the people who participated in the AI forecasting thing you cite here, and the experience was unfortunately very bad due to various reasons</p>
+<p>i would strongly push back on the idea that the people selected were in any sense "top forecasters"</p>
+<p>Lao Mein writes <a href="https://www.lesswrong.com/posts/AZHHEPYWvTovvtikz/human-level-diplomacy-was-my-fire-alarm" target="_blank" rel="noopener">Human-level Diplomacy was my fire alarm</a> (<a href="http://web.archive.org/web/20221202162217/https://www.lesswrong.com/posts/AZHHEPYWvTovvtikz/human-level-diplomacy-was-my-fire-alarm" target="_blank" rel="noopener">a</a>).</p>
+<p>Nikos Bosse is working on a <a href="https://forum.effectivealtruism.org/posts/H7xWzvwvkyywDAEkL/creating-a-database-for-base-rates" target="_blank" rel="noopener">database of baserates</a> (<a href="http://web.archive.org/web/20221223122549/https://forum.effectivealtruism.org/posts/H7xWzvwvkyywDAEkL/creating-a-database-for-base-rates" target="_blank" rel="noopener">a</a>).</p>
+<p>A newsletter from Cultivate Labs highlights an article on <a href="https://www.cultivatelabs.com/posts/crowd-forecasting-and-effective-altruism" target="_blank" rel="noopener">Crowd Forecasting and Effective Altruism</a> (<a href="http://web.archive.org/web/20221223123956/https://www.cultivatelabs.com/posts/crowd-forecasting-and-effective-altruism" target="_blank" rel="noopener">a</a>).</p>
+<p>Ben West looks at the <a href="https://ea.greaterwrong.com/posts/5mghcxCabxuaK4WTs/ycombinator-fraud-rates" target="_blank" rel="noopener">rate of fraud in YCombinator startups</a> (<a href="https://web.archive.org/web/20230106175234/https://ea.greaterwrong.com/posts/5mghcxCabxuaK4WTs/ycombinator-fraud-rates" target="_blank" rel="noopener">a</a>), and finds that "1-2% of $100M+ YCombinator-backed companies have faced serious allegations of fraud".</p>
+<p>This <a href="https://www.washingtonpost.com/news/wonk/wp/2016/03/18/how-the-likelihood-of-breaking-up-changes-as-time-goes-by/" target="_blank" rel="noopener">old Washington Post article</a> (<a href="http://web.archive.org/web/20211005190327/https://www.washingtonpost.com/news/wonk/wp/2016/03/18/how-the-likelihood-of-breaking-up-changes-as-time-goes-by/" target="_blank" rel="noopener">a</a>) shows the annual risk of breakup for married and unmarried couples:</p>
+<p>Cultivate Labs' CEO <a href="https://www.cultivatelabs.com/posts/2022-in-the-rearview" target="_blank" rel="noopener">reviews</a> (<a href="http://web.archive.org/web/20221223123956/https://www.cultivatelabs.com/posts/2022-in-the-rearview" target="_blank" rel="noopener">a</a>) his company's activities in 2022. In particular:</p>
+<p>The INFER project run by UMD&rsquo;s ARLIS will be announcing a co-sponsored forecasting tournament with a significant player in the AI space next month, and will also be formally launching a U.S. Government-wide forecasting platform in the spring.</p>
+<p>The European Commission, an organ of the European Union, has <a href="https://commission.europa.eu/statistics/economic-forecasts-and-trends_en" target="_blank" rel="noopener">a page with economic forecasts and trends</a> (<a href="http://web.archive.org/web/20221225144109/https://commission.europa.eu/statistics/economic-forecasts-and-trends_en" target="_blank" rel="noopener">a</a>). Its economic forecasts are <a href="https://economy-finance.ec.europa.eu/economic-forecast-and-surveys/economic-forecasts_en" target="_blank" rel="noopener">here</a> (<a href="http://web.archive.org/web/20221227042949/https://economy-finance.ec.europa.eu/economic-forecast-and-surveys/economic-forecasts_en" target="_blank" rel="noopener">a</a>) and <a href="https://ec.europa.eu/economy_finance/publications/european_economy/forecasts/index_en.htm" target="_blank" rel="noopener">here</a> (<a href="http://web.archive.org/web/20221101065157/https://ec.europa.eu/economy_finance/publications/european_economy/forecasts/index_en.htm" target="_blank" rel="noopener">a</a>). It would be a neat research project to track results and check whether they are calibrated. It would also be easy to propose possible improvements: use range forecasts instead of point estimates, and use very liquid markets if you really care.</p>
+<p>Here are <a href="https://www.visitbritain.org/2023-tourism-forecast" target="_blank" rel="noopener">some forecasts on British tourism</a> (<a href="http://web.archive.org/web/20230104165249/https://www.visitbritain.org/2023-tourism-forecast" target="_blank" rel="noopener">a</a>).</p>
+<p>Pinterest has a flashy <a href="https://business.pinterest.com/en-us/pinterest-predicts/" target="_blank" rel="noopener">Pinterest Predicts</a> (<a href="http://web.archive.org/web/20230104173909/https://business.pinterest.com/en-us/pinterest-predicts/" target="_blank" rel="noopener">a</a>) webpage (methodology explained <a href="https://business.pinterest.com/en-us/blog/how-we-forecast-trends-pinterest-predicts/" target="_blank" rel="noopener">here</a> (<a href="http://web.archive.org/web/20221228013359/https://business.pinterest.com/en-us/blog/how-we-forecast-trends-pinterest-predicts/" target="_blank" rel="noopener">a</a>)). Pinterest is used by people to plan stuff, and Pinterest can rely on the law of straight lines to predict that trends that are growing will continue to do so.</p>
+<p><a href="https://sci-hub.se/https://onlinelibrary.wiley.com/doi/epdf/10.1111/1911-3846.12144" target="_blank" rel="noopener">Does (a measure of) CEO overconfidence affect management forecasting and subsequent earnings management?</a> (<a href="https://web.archive.org/web/20230104231627/https://sci-hub.se/https://onlinelibrary.wiley.com/doi/epdf/10.1111/1911-3846.12144" target="_blank" rel="noopener">a</a>). A paper finds that it does.</p>
+<p>The International Journal of Forecasting has a <a href="https://www.sciencedirect.com/journal/international-journal-of-forecasting/vol/38/issue/4" target="_blank" rel="noopener">special issue</a> (<a href="https://web.archive.org/web/20230000000000*/https://www.sciencedirect.com/journal/international-journal-of-forecasting/vol/38/issue/4" target="_blank" rel="noopener">a</a>) on the M5 competition.</p>
+<p>The Wall Street Journal reports on how companies use <a href="https://www.wsj.com/articles/unilever-cfo-struggles-with-forecasting-accuracy-amid-high-inflation-11666904322" target="_blank" rel="noopener">uncertainty and rising energy prices as the justification for increasing price</a> (<a href="http://web.archive.org/web/20230105211045/https://www.wsj.com/articles/unilever-cfo-struggles-with-forecasting-accuracy-amid-high-inflation-11666904322" target="_blank" rel="noopener">a</a>). You could take them at their word. On the other hand, in Spain, where food prices have risen a whole lot, some people view these as illegitimate cash grabs.</p>
+<p><a href="https://www.thelancet.com/journals/lanpub/article/PIIS2468-2667%2822%2900203-1/fulltext" target="_blank" rel="noopener">This paper</a> (<a href="http://web.archive.org/web/20230105002641/https://www.thelancet.com/journals/lanpub/article/PIIS2468-2667%2822%2900203-1/fulltext" target="_blank" rel="noopener">a</a>) tries to forecast the burden on the Chinese health system by tracking a large sample of older people.</p>
+<p>Amazon offers some <a href="https://techcrunch.com/2022/11/29/aws-brings-natural-language-forecasting-queries-to-quicksight-q" target="_blank" rel="noopener">automated ML forecasting</a> (<a href="https://web.archive.org/web/20230000000000*/https://techcrunch.com/2022/11/29/aws-brings-natural-language-forecasting-queries-to-quicksight-q" target="_blank" rel="noopener">a</a>), as does <a href="https://www.oracle.com/sk/artificial-intelligence/forecasting/" target="_blank" rel="noopener">Oracle</a> (<a href="http://web.archive.org/web/20230105002702/https://www.oracle.com/sk/artificial-intelligence/forecasting/" target="_blank" rel="noopener">a</a>).</p>
+<h3>Longform</h3>
+<p>Jared Leibowich looks at <a href="https://asteriskmag.com/issues/1/modeling-the-end-of-monkeypox" target="_blank" rel="noopener">Modeling the End of Monkeypox</a> (<a href="http://web.archive.org/web/20221122015655/https://asteriskmag.com/issues/1/modeling-the-end-of-monkeypox" target="_blank" rel="noopener">a</a>) in a new EA magazine, <a href="https://asteriskmag.com/" target="_blank" rel="noopener">Asterisk</a> (<a href="http://web.archive.org/web/20221212215202/https://asteriskmag.com/" target="_blank" rel="noopener">a</a>).</p>
+<p><a href="https://www.metacausal.com/givewells-uncertainty-problem/" target="_blank" rel="noopener">This blogpost</a> (<a href="http://web.archive.org/web/20221222172413/https://www.metacausal.com/givewells-uncertainty-problem/" target="_blank" rel="noopener">a</a>) won $20k from GiveWell&rsquo;s "Change our Mind Contest." It looks at how their analyses could be improved by considering the uncertainty in their estimates, and does this at some depth, providing examples and recommendations.</p>
+<p>Prominent anti-vaccine personality Steve Kirsh offered <a href="https://stevekirsch.substack.com/p/1m-bet-rules" target="_blank" rel="noopener">$500k bets</a> (<a href="http://web.archive.org/web/20221104130431/https://stevekirsch.substack.com/p/1m-bet-rules" target="_blank" rel="noopener">a</a>) on the result of a public debate on whether vaccines save lives or not. <a href="https://www.rootclaim.com/" target="_blank" rel="noopener">Rootclaim</a> (<a href="https://web.archive.org/web/20230104080248/https://www.rootclaim.com/" target="_blank" rel="noopener">a</a>), a hardcore Bayesian analysis organization, put significant efforts into doing their homework, and <a href="https://blog.rootclaim.com/rootclaim-accepts-500000-challenge-on-covid-vaccine-safety-efficacy/" target="_blank" rel="noopener">accepted the bet</a> (<a href="http://web.archive.org/web/20221129133112/https://blog.rootclaim.com/rootclaim-accepts-500000-challenge-on-covid-vaccine-safety-efficacy/" target="_blank" rel="noopener">a</a>). Then Kirsh <a href="https://stevekirsch.substack.com/p/1m-bet-rules" target="_blank" rel="noopener">dishonourably chickened out</a> (<a href="http://web.archive.org/web/20221104130431/https://stevekirsch.substack.com/p/1m-bet-rules" target="_blank" rel="noopener">a</a>). A transcript of the negotiations can be found <a href="https://www.skirsch.com/covid/SaarWilf.pdf" target="_blank" rel="noopener">here</a> (<a href="http://web.archive.org/web/20221224061743/https://www.skirsch.com/covid/SaarWilf.pdf" target="_blank" rel="noopener">a</a>).</p>
+<p>The Swift Centre has a report on <a href="https://www.swiftcentre.org/what-would-be-the-consequences-of-a-nuclear-weapon-being-used-in-the-russia-ukraine-war/" target="_blank" rel="noopener">what would happen if Russia uses a nuclear weapon</a> (<a href="http://web.archive.org/web/20230104231909/https://www.swiftcentre.org/what-would-be-the-consequences-of-a-nuclear-weapon-being-used-in-the-russia-ukraine-war/" target="_blank" rel="noopener">a</a>), and is accepting commissions for topics to forecasting. They can be contacted at info@swiftcentre.org.</p>
+<p>Andrew Gelman <a href="https://statmodeling.stat.columbia.edu/2022/11/04/new-version-of-posteriordb-a-database-of-posterior-distributions-for-evaluating-bayesian-computation-algorithms/" target="_blank" rel="noopener">points</a> (<a href="http://web.archive.org/web/20230104231944/https://statmodeling.stat.columbia.edu/2022/11/04/new-version-of-posteriordb-a-database-of-posterior-distributions-for-evaluating-bayesian-computation-algorithms/" target="_blank" rel="noopener">a</a>) to <a href="https://github.com/stan-dev/posteriordb" target="_blank" rel="noopener">PosteriorDB</a> (<a href="http://web.archive.org/web/20230105002803/https://github.com/stan-dev/posteriordb" target="_blank" rel="noopener">a</a>) a database of posteriors.</p>
+<p>Friend of the newsletter Pratik Chougule recently published <a href="https://brill.com/display/title/63192" target="_blank" rel="noopener">American Universities in the Middle East and U.S. Foreign Policy</a> (<a href="http://web.archive.org/web/20230105002822/https://brill.com/display/title/63192" target="_blank" rel="noopener">a</a>). It seems oddly specific, so I'd instead recommend his older &amp; cheaper <a href="https://www.amazon.com/How-Make-Money-Political-Predictions-ebook/dp/B01KEGLRJ2" target="_blank" rel="noopener">How to Make Money from Political Predictions</a> (<a href="https://web.archive.org/web/20230000000000*/https://www.amazon.com/How-Make-Money-Political-Predictions-ebook/dp/B01KEGLRJ2" target="_blank" rel="noopener">a</a>).</p>
+<p>Michael Story writes about <a href="https://mwstory.substack.com/p/why-i-generally-dont-recommend-internal" target="_blank" rel="noopener">why he generally doesn't recommend internal prediction markets or forecasting tournaments to organisations</a> (<a href="https://web.archive.org/web/20230106175846/https://mwstory.substack.com/p/why-i-generally-dont-recommend-internal" target="_blank" rel="noopener">a</a>).</p>
+<h2>In the News</h2>
+<p>Walter Frick of <a href="https://nonrival.pub/" target="_blank" rel="noopener">Nonrival</a> (<a href="http://web.archive.org/web/20221222000715/https://nonrival.pub/" target="_blank" rel="noopener">a</a>) writes <a href="https://www.niemanlab.org/2022/12/journalists-wake-up-to-the-power-of-prediction-markets/" target="_blank" rel="noopener">Journalists wake up to the power of prediction markets</a> (<a href="http://web.archive.org/web/20230105002710/https://www.niemanlab.org/2022/12/journalists-wake-up-to-the-power-of-prediction-markets/" target="_blank" rel="noopener">a</a>), a short piece introducing the concept and resources to journalists.</p>
+<p>The New York Times has an article (<a href="https://archive.is/FLB4p" target="_blank" rel="noopener">a</a>) on "Forecasting the Future of Election Prediction Markets". It has this nice tidbit:</p>
+<p>PredictIt is something of a hybrid. It is a joint venture. One partner is Victoria University of Wellington, a New Zealand institution. The other is Aristotle, a for-profit American political consulting, compliance, data and software company, whose founder, John Aristotle Phillips, first gained national attention in 1976 as &ldquo;the A-bomb kid&rdquo; &mdash; a Princeton undergraduate who successfully designed an atomic bomb in a physics class project.</p>
+<p>I also find it interesting how the NYT article mostly cites academics rather than, e.g., <a href="https://comments.cftc.gov/PublicComments/ViewComment.aspx?id=69699" target="_blank" rel="noopener">Sam Altman's comments to the CFTC</a> (<a href="https://web.archive.org/web/20230106194025/https://comments.cftc.gov/PublicComments/ViewComment.aspx?id=69699" target="_blank" rel="noopener">a</a>) or other <a href="https://comments.cftc.gov/PublicComments/CommentList.aspx?id=7311" target="_blank" rel="noopener">interesting figures</a> (<a href="https://web.archive.org/web/20230000000000*/https://comments.cftc.gov/PublicComments/CommentList.aspx?id=7311" target="_blank" rel="noopener">a</a>).</p>
+<p>Vegas Slots Online has a short article <a href="https://www.vegasslotsonline.com/news/2022/10/31/cftc-ready-to-deny-political-betting-request-from-kalshi/" target="_blank" rel="noopener">CFTC Ready to Deny Political Betting Request From Kalshi as PredictIt Levies a Lawsuit</a> (<a href="http://web.archive.org/web/20221101221514/https://www.vegasslotsonline.com/news/2022/10/31/cftc-ready-to-deny-political-betting-request-from-kalshi/" target="_blank" rel="noopener">a</a>).</p>
+<p>El Pa&iacute;s, a major Spanish newspaper, <a href="https://english.elpais.com/usa/2022-11-01/us-election-forecast-republicans-will-control-the-house-the-senate-is-too-close-to-call.html" target="_blank" rel="noopener">directly embedded prediction markets</a> (<a href="http://web.archive.org/web/20221208220725/https://english.elpais.com/usa/2022-11-01/us-election-forecast-republicans-will-control-the-house-the-senate-is-too-close-to-call.html" target="_blank" rel="noopener">a</a>) in its reporting on the US election.</p>
+<p>Newsweek, on <a href="https://www.newsweek.com/marjorie-taylor-greene-chances-losing-georgia-re-election-1756671" target="_blank" rel="noopener">Marjorie Taylor Greene's Chances of Losing Georgia Re-election</a> (<a href="http://web.archive.org/web/20230106180010/https://www.newsweek.com/marjorie-taylor-greene-chances-losing-georgia-re-election-1756671" target="_blank" rel="noopener">a</a>).</p>
+<p>Fast Company has a lengthy profile on <a href="https://www.fastcompany.com/90796054/inside-the-wild-subculture-of-traders-who-bet-on-elections" target="_blank" rel="noopener">"the wild subculture of traders who bet on elections"</a> (<a href="http://web.archive.org/web/20221109203752/https://www.fastcompany.com/90796054/inside-the-wild-subculture-of-traders-who-bet-on-elections" target="_blank" rel="noopener">a</a>).</p>
+<p><a href="https://www.theatlantic.com/technology/archive/2022/11/political-betting-elections-forecasting-future/672113/" target="_blank" rel="noopener">The Atlantic</a> (<a href="http://web.archive.org/web/20221202193500/https://www.theatlantic.com/technology/archive/2022/11/political-betting-elections-forecasting-future/672113/" target="_blank" rel="noopener">a</a>): "In the eight years since PredictIt began, online sports gambling went from being outlawed nearly everywhere in the country to a booming industry... In this context, the crackdown on political betting seems somewhat silly... As it turns out, on another site, Insight Prediction, you can bet on PredictIt&rsquo;s survival. The price of Yes, as of this writing, is 10 cents. Even if the CFTC follows through on its initial decision to shut the site down, it&rsquo;s hard not to feel that PredictIt has, in some more meaningful way, already won."</p>
+<p>The Financial Times reviews <a href="https://www.ft.com/content/9a3b4b78-b18b-4d1f-b28b-05a73525aa61" target="_blank" rel="noopener">a few of the wackier $1M investments</a> (<a href="http://web.archive.org/web/20221227114544/https://www.ft.com/content/9a3b4b78-b18b-4d1f-b28b-05a73525aa61" target="_blank" rel="noopener">a</a>) FTX made, including Manifold Markets.</p>
+<p>Vox <a href="https://www.vox.com/future-perfect/2022/12/31/23509593/2022-predictions-macron-bolsanaro-covid-inflation-unemployment-climate-change-olympics" target="_blank" rel="noopener">reviews</a> (<a href="http://web.archive.org/web/20230105091649/https://www.vox.com/future-perfect/2022/12/31/23509593/2022-predictions-macron-bolsanaro-covid-inflation-unemployment-climate-change-olympics" target="_blank" rel="noopener">a</a>) its yearly numerical predictions and makes new ones.</p>
+<h3>Extra: The tax-evaded Nazi money which influences German politics and US/NATO relationships has opened a new forecasting platform.</h3>
+<p>A smallish company <a href="https://www.campaignlive.co.uk/article/truth-comes-bertelsmann-admits-nazi-past/160317" target="_blank" rel="noopener">rises</a> (<a href="http://web.archive.org/web/20230105002941/https://www.campaignlive.co.uk/article/truth-comes-bertelsmann-admits-nazi-past/160317" target="_blank" rel="noopener">a</a>) to become a major German publisher during the <a href="https://en.wikipedia.org/wiki/Bertelsmann#1933_to_1945" target="_blank" rel="noopener">Nazi times</a>. After World War II, the now disgraced father gives control of the company to one of his surviving sons. The son manages the business competently, and greatly expands it. In an attempted tax evasion scheme, he divides the company's stock into a small percentage of voting stock and a large percentage of non-voting stock which he gives to a private foundation&mdash;I think this is the same trick which failed for the <a href="https://en.wikipedia.org/wiki/Ford_Foundation" target="_blank" rel="noopener">Ford Foundation</a> (<a href="http://web.archive.org/web/20230105003036/https://en.wikipedia.org/wiki/Ford_Foundation" target="_blank" rel="noopener">a</a>).</p>
+<p>Except that this time, the <a href="https://taz.de/!5137745/" target="_blank" rel="noopener">trick</a><a href="http://www.bertelsmannkritik.de/index.htm" target="_blank" rel="noopener">succeeds</a> (<a href="http://web.archive.org/web/20230105003044/http://www.bertelsmannkritik.de/index.htm" target="_blank" rel="noopener">a</a>), and after the death of the founder, it allows the family to keep control of assets while minimizing tax exposure. But the logic of the scheme requires that the company give out as few dividends as possible&mdash;because they would then be trapped inside the foundation and be difficult to get out. Which is why Bertelsmann has greatly expanded and is now a $30B behemoth which owns <a href="https://en.wikipedia.org/wiki/Random_House" target="_blank" rel="noopener">Penguin Random House</a> (<a href="http://web.archive.org/web/20221224150408/https://en.wikipedia.org/wiki/Random_House" target="_blank" rel="noopener">a</a>) as one of many items in an absurdly <a href="https://en.wikipedia.org/wiki/List_of_assets_owned_by_Bertelsmann" target="_blank" rel="noopener">long list of assets</a> (<a href="http://web.archive.org/web/20221031225743/https://en.wikipedia.org/wiki/List_of_assets_owned_by_Bertelsmann" target="_blank" rel="noopener">a</a>). Amusingly, they also <a href="https://en.wikipedia.org/wiki/Brigitte_Mohn#Career" target="_blank" rel="noopener">have the same person</a> (<a href="https://web.archive.org/web/20221114210641/https://en.wikipedia.org/wiki/Brigitte_Mohn#Career" target="_blank" rel="noopener">a</a>) represent the interest of the family and of the foundation.</p>
+<p>Cover of the "Heimat, wider Heimat" book, which translates to something like "Motherland, oh Motherland again", published by Bertelsmann. Note dog whistle connotations of <a href="https://en.wikipedia.org/wiki/Heimat#Modern_history" target="_blank" rel="noopener">Heimat</a>. The author, Gustav Schr&ouml;er, is one of four authors that I could quickly find that were both published by Bertelsmann and signed the "<a href="https://de.wikipedia.org/wiki/Gel%C3%B6bnis_treuester_Gefolgschaft" target="_blank" rel="noopener">Declaration of Allegiance of German Writers</a> (<a href="http://web.archive.org/web/20230105003103/https://de.wikipedia.org/wiki/Gel%C3%B6bnis_treuester_Gefolgschaft" target="_blank" rel="noopener">a</a>)" to Adolf Hitler. The others are Rudolf G. Binding, Otto Flake and Fritz M&uuml;ller-Partenkirchen. The case of Otto Flake is particularly interesting, since Bertelsmann rescued him from poverty in 1958 by reprinting old books of his.</p>
+<p>Now, the Bertelsmann foundation has made a small contribution to the forecasting world by starting the <a href="https://www.rangeforecasting.org/" target="_blank" rel="noopener">Range Forecasting</a> (<a href="http://web.archive.org/web/20230105003141/https://www.rangeforecasting.org/" target="_blank" rel="noopener">a</a>) platform, which runs on Cultivate Labs software. Per a recent Cultivate Labs newsletter:</p>
+<p>Earlier this year, the Bertelsmann Stiftung and Bertelsmann Foundation, in partnership with Cultivate Labs, launched RANGE (Rethinking Assumptions in a New Geostrategic Environment) to forecast on topics critical to the transatlantic relationship. RANGE asks questions related to systemic rivalry with China, climate change, democracy, geopolitics, trade, and economics, all to gain a greater perspective of the transatlantic relationship and to provide analysis and recommendations for U.S. and European policymakers.&nbsp;</p>
+<p>At a critical time for strengthening global relations, the Stiftung and Foundation aim to engage an international audience in understanding how the transatlantic relationship affects us all, and how it can and should be shaped for the future. Read our recent announcement about the partnership and learn more at rangeforecasting.org.&nbsp; &nbsp; RANGE was featured this week at the 2022 Futures Forum in M&uuml;nster, Germany, a side event of the G7 minister&rsquo;s meeting, which brought together American and German experts and rising leaders from civil society, academia, the private sector, and government to discuss transatlantic relations and the intersection of democracy and technology.</p>
+<p>Earlier today at the Forum, Cultivate Labs CEO Adam Siegel spoke alongside Bertelsmann Foundation Executive Director Irene Braam about RANGE and the ways that crowd forecasting can help us better understand and strengthen transatlantic relations.</p>
+<p>I do think that this new forecasting platform might be of some use. And I want to express my continued high regard for Cultivate Labs as one of the few platforms that have the proven ability to bring forth a new platform into existence, and maintain it through time. But I guess that reputational laundering of billionaires' money is easier to notice when it is billionaires I don't care much about. And in this particular case, the provenance of the money seems so illegitimate, so rotten, as to be almost comical.</p>
+<h2>Yearly housekeeping</h2>
+<p><a href="https://forms.gle/L6kv9GKh5eSf2Kmb6" target="_blank" rel="noopener">Here</a> (<a href="https://web.archive.org/web/20230106180045/https://docs.google.com/forms/d/e/1FAIpQLSd3eFDhdDReceLrSly4gWmGliHdCX7LNEJygGUEttkLi57M_Q/viewform?usp=send_form#short_url=https://forms.gle/L6kv9GKh5eSf2Kmb6" target="_blank" rel="noopener">a</a>) is my yearly feedback form for this newsletter. I care most about readers' thoughts on whether this newsletter should be posted once a month or once every two months, and about freeform thoughts.</p>
+<p>Also note that as the price I assign to my time rises, I'm becoming more ambivalent about whether to continue publishing this newsletter. If you have strong feelings about whether this newsletter should continue existing, consider becoming a paid subscriber, because a) I consider that a strong signal that I should continue writing this newsletter, b) I like the money, and c) the rate of current paid subscriptions is a pitiful <a href="https://substack.com/going-paid-guide#grow-paid-list" target="_blank" rel="noopener">1.6%</a> (<a href="https://web.archive.org/web/20230000000000*/https://substack.com/going-paid-guide#grow-paid-list" target="_blank" rel="noopener">a</a>).</p>
+<p>Note to the future: All links are added automatically to the Internet Archive, using this <a href="https://github.com/NunoSempere/longNowForMd" target="_blank" rel="noopener">tool</a> (<a href="http://web.archive.org/web/20230105003212/https://github.com/NunoSempere/longNowForMd" target="_blank" rel="noopener">a</a>). "(a)" for archived links was inspired by <a href="https://www.flightfromperfection.com/" target="_blank" rel="noopener">Milan Griffes</a> (<a href="http://web.archive.org/web/20230105003223/https://www.flightfromperfection.com/" target="_blank" rel="noopener">a</a>), <a href="https://www.andzuck.com/" target="_blank" rel="noopener">Andrew Zuckerman</a> (<a href="http://web.archive.org/web/20220316214638/https://www.andzuck.com/" target="_blank" rel="noopener">a</a>), and <a href="https://guzey.com/" target="_blank" rel="noopener">Alexey Guzey</a> (<a href="http://web.archive.org/web/20230101090040/https://guzey.com/" target="_blank" rel="noopener">a</a>).</p>
+<p>&gt; If I had to put my money where my mouth is, my mouth wouldn&rsquo;t be very busy. I&rsquo;m just sayin&rsquo;&hellip; &mdash; <a href="https://statmodeling.stat.columbia.edu/2022/10/27/you-can-read-for-free-but-comments-cost-money-or-is-it-the-other-way-around/" target="_blank" rel="noopener">Anonymous commenter</a> (<a href="https://web.archive.org/web/20230000000000*/https://statmodeling.stat.columbia.edu/2022/10/27/you-can-read-for-free-but-comments-cost-money-or-is-it-the-other-way-around/" target="_blank" rel="noopener">a</a>)</p>

blog/2023/01/07/forecasting-newsletter-november-december-2022/index.md

@@ -0,0 +1,295 @@
+Forecasting Newsletter for November and December 2022
+================
+
+## Highlights
+
+- PredictIt nears its [probable demise](https://insightprediction.com/m/18505/will-predictit-survive)
+- American Civics Exchange offers [political betting](https://otc.amciv.com/) to Americans using weird legal loophole
+- Forecasting community member Avraham Eisenberg [arrested for $100M+ theft](https://www.coindesk.com/policy/2022/12/27/mango-markets-exploiter-eisenberg-arrested-in-puerto-rico/) ([a](https://web.archive.org/web/20230106173959/https://www.coindesk.com/policy/2022/12/27/mango-markets-exploiter-eisenberg-arrested-in-puerto-rico/)).
+- Forecasting Research Institute [launches publicly](https://ea.greaterwrong.com/posts/kEd5qWwg8pZjWAeFS/announcing-the-forecasting-research-institute-we-re-hiring)
+- Blogpost [suggests that GiveWell use uncertainty](https://www.metacausal.com/givewells-uncertainty-problem/), wins $20k
+- Contrarian [offers $500k bet](https://stevekirsch.substack.com/p/1m-bet-rules), then chickens out
+- Walter Frick writes a [resource to introduce journalists to prediction markets](https://www.niemanlab.org/2022/12/journalists-wake-up-to-the-power-of-prediction-markets/)
+- Yearly feedback form
+
+## Index
+
+- Prediction Markets and Forecasting Platforms
+  - PredictIt
+  - American Civics Exchange
+  - Polymarket
+  - Insight Prediction
+  - Kalshi
+  - INFER
+  - Metaculus
+  - Manifold
+  - Odds and Ends
+- Opportunities
+- Research
+  - Shortform
+  - Longform
+- In the News
+- Extra: The tax-evaded Nazi money which influences German politics and US/NATO relationships has opened a new forecasting platform.
+- Yearly housekeeping
+
+Browse past newsletters [here](https://forecasting.substack.com/) ([a](http://web.archive.org/web/20230105001738/https://forecasting.substack.com/)), or view this newsletter on the EA forum here. If you have a content suggestion or want to reach out, you can leave a comment or find me on [Twitter](https://twitter.com/NunoSempere). 
+## Prediction Markets and Forecasting Platforms
+
+### PredictIt
+
+Racing against the clock, PredictIt is trying to get permission from the CFTC to continue existing. From PredictIt’s newsletter:
+
+> As you may know, the Commodity Futures Trading Commission (CFTC) decided in August to revoke the authorization that allowed PredictIt to operate [effective Feb. 15, 2023](https://www.predictit.org/platform-announcements) ([a](http://web.archive.org/web/20221223063826/https://www.predictit.org/platform-announcements)) ([original CFTC source](https://www.cftc.gov/PressRoom/PressReleases/8567-22) ([a](http://web.archive.org/web/20221217222553/https://www.cftc.gov/PressRoom/PressReleases/8567-22))). More than a dozen of your fellow PredictIt traders, as well as academic data users and PredictIt’s parent company Aristotle, have challenged this decision in federal court with the goal of keeping election markets open and operating past the CFTC’s arbitrary Feb. 15, 2023, deadline.
+> 
+> Given the time-sensitive nature of this fight, the [plaintiffs filed a motion](https://www.casino.org/news/predictit-to-seek-cftc-injunction-in-appeals-court-after-lower-court-fails-to-act/) ([a](http://web.archive.org/web/20230103080014/https://www.casino.org/news/predictit-to-seek-cftc-injunction-in-appeals-court-after-lower-court-fails-to-act/)) last week to move the case to the United States Court of Appeals for the Fifth Circuit, which is the quickest path towards attaining justice for our traders and academic partners. We understand that legal battles do not generally make for exhilarating newsletter content, but as valued members of our community, we want you to know that we’re fighting on every available battlefield for the future of PredictIt and political prediction markets.
+> 
+> To that end, Aristotle, has also applied to the CFTC for permission to operate a Designated Contract Market (DCM), which will offer event contracts that include certain political outcomes. We’re well along in that process and hope to have approval in the coming months.
+> 
+> If approved, PredictIt Exchange will list many of the same contracts that you love: polling averages, nominations, confirmations and legislative outcomes, among other topics.
+> 
+> This next step toward becoming a regulated entity has been a long-time goal of the PredictIt team. We’ll be in touch soon with more information about how to sign up for PredictIt Exchange and other exciting developments in the works for next year. Stay tuned\!
+ 
+### American Civics Exchange
+
+The newly created American Civics Exchange is offering [over-the-counter betting](https://otc.amciv.com/dashboard) ([a](http://web.archive.org/web/20221122165636/https://otc.amciv.com/dashboard)) on political events.
+
+I'm not clear on how [this is legal](https://en.wikipedia.org/wiki/Over-the-counter_%28finance%29) ([a](https://web.archive.org/web/20230106180304/https://en.wikipedia.org/wiki/Over-the-counter_%28finance%29)), but readers might consult their "What is ACE otc's regulatory framework?" section in their [FAQ](https://otc.amciv.com/page/faq) ([a](http://web.archive.org/web/20230105001904/https://otc.amciv.com/page/faq)). 
+
+The man behind the thing is [Filip Pidot](https://twitter.com/FlipPidot) ([a](https://web.archive.org/web/20230106192455/https://twitter.com/FlipPidot)), who previously ran the [Old Bull TV](https://www.youtube.com/@OldBullTV/videos) ([a](http://web.archive.org/web/20230105002037/https://www.youtube.com/@OldBullTV/videos)) youtube channel, and is generally considered a respectable community member.
+
+### Polymarket
+
+Polymarket deploys an [adapter](https://github.com/Polymarket/uma-ctf-adapter) ([a](http://web.archive.org/web/20221013234314/https://github.com/Polymarket/uma-ctf-adapter)) between its Keynesian beauty contest resolution mechanism, [UMA](https://umaproject.org/) ([a](http://web.archive.org/web/20230104180400/https://umaproject.org/)), and actual resolutions. There is an "emergencyResolve" feature, which judging by the name could be used to override or bypass the UMA resolution. This is marginally concerning, because it could be used to siphon money away from markets, by betting on the less likely outcome and then resolving to it.
+
+![Image of the Polymarket-UMA adapter](https://i.imgur.com/vsep53y.jpg)
+
+Ultimately, I don't think this matters very much, because if Polymarket was compromised, users' wallets could probably be drained through some change in the webpage. Still, this downgrades UMA from its previous status as a source of truth to merely a convenient resolution mechanism,
+
+### Insight Prediction
+
+Insight Prediction [introduced](https://twitter.com/Insight_Predict/status/1587428761456193536) ([a](http://web.archive.org/web/20230105001841/https://twitter.com/Insight_Predict/status/1587428761456193536)) some innovations around "sudden death markets". It's difficult to do market-making for markets about discrete events, because if the event happens, traders will quickly make bets and rake in profit before the market-maker notices. And so:
+
+> what we've implemented is the ability to have markets where we return all bets after a particular event has transpired. Bets placed before the event will be honored, while bets placed after will be returned. This of course requires bets in the market to be locked (72 hours)
+
+You can see this functionality in this market: [Will Elon Musk Father Another Child Before August 2023?](https://insightprediction.com/m/67960/will-elon-musk-father-another-child-by-august-2023) ([a](http://web.archive.org/web/20230105001846/https://insightprediction.com/m/67960/will-elon-musk-father-another-child-by-august-2023)) market.
+
+### Kalshi
+
+Kalshi [updates their API](https://kalshi.com/blog/apiv2-is-here/) ([a](https://web.archive.org/web/20230106192534/https://kalshi.com/blog/apiv2-is-here/)) and, separately, gets [lampooned in Hacker News](https://news.ycombinator.com/item?id=33696486) ([a](https://web.archive.org/web/20230106174123/https://news.ycombinator.com/item?id=33696486)):
+
+> That's neat but how does one hedge a $800k loan with a max position of $25k? Idea seems spurious. The difference is substantially higher. Compare a pre-hike 2.8% with a present 6.8%. Your $25k hedge is going to be pointless.
+> 
+> > Before Kalshi, markets that allowed you to trade on economically relevant events were illegal or unregulated.
+> 
+> Totally untrue. PredictIt was legal and regulated and well-loved for many years, operating with the permission of the CFTC under a no-action letter. Then Kalshi hired former CFTC commissioner Brian Quintenz and soon, PredictIt was suddenly deemed by the CFTC to have committed still-unenumerated violations of the no-action letter.
+> 
+> This is a rotten way to do business and shame on YC for being involved in it.
+
+### INFER
+
+INFER has a few [quarterly reports](https://www.infer-pub.com/archive) ([a](http://web.archive.org/web/20230105002053/https://www.infer-pub.com/archive)) on their forecasts on Synthetic Biology, AI and Microelectronics. It also has a [$5.25k](https://www.infer-pub.com/future-bowl-tournament) ([a](http://web.archive.org/web/20230105002109/https://www.infer-pub.com/future-bowl-tournament)) tournament.
+
+When Metaculus got a [$5.5M grant](https://www.openphilanthropy.org/grants/metaculus-platform-development/) ([a](http://web.archive.org/web/20230105002123/https://www.openphilanthropy.org/grants/metaculus-platform-development/)) earlier this year, I could mostly see this reverberating, them hiring more people, a few teams being created, people I was keeping tabs on getting hired, more forecasting contests happening, and so on. You know, $5M is a small fortune, and I try to listen to the pulse of these things. Manifold Markets got built on top of $1M.
+
+So for a while now, it has been very unclear to me where the [$8M that INFER's parent organization got from Open Philanthropy](https://www.openphilanthropy.org/grants/applied-research-laboratory-for-intelligence-and-security-forecasting-platforms/) ([a](http://web.archive.org/web/20230105002137/https://www.openphilanthropy.org/grants/applied-research-laboratory-for-intelligence-and-security-forecasting-platforms/)) was going. Things just weren't very visibly different from what I would expect to see if that grant hadn't really happened. INFER's forecasting rewards continued to be pretty small.
+
+Taking a page from [Andrew Gelman](https://statmodeling.stat.columbia.edu/) ([a](http://web.archive.org/web/20230101023816/https://statmodeling.stat.columbia.edu/)), who is extremely meek when pointing these kinds of issues out, there could be many explanations. For example, it's possible that it does add up, that infrastructure and putting these kinds of reports out does take that much money. Or that they are spending the money slowly and sustainably for the long term. Or that the University of Maryland administration takes a really large chunk of funds. I am also assuming that the $8M in two years for two platforms doesn't correspond to something in the very rough neighbourhood of $2M per year per platform, but it could be that that's not the case. It's also possible that the INFER forecasting sphere and the sphere that I pay the most attention to don't overlap as much, which could be a positive. Still, the difference between the funds they receive and the impact that I perceive as for a while a small mystery to me.
+
+Now, in its yearly review, INFER [mentions](https://www.infer-pub.com/the-pub/season-review-2022) ([a](http://web.archive.org/web/20221222200606/https://www.infer-pub.com/the-pub/season-review-2022)) working on "an internal U.S. Government-wide site" for 2023. That does seem like it could absorb large amounts of funds. Still, personally, I'd love to see a bill of how much was spent where.
+
+### Metaculus
+
+Metaculus held a [Million Predictions Hackathon](https://scribe.froth.zone/announcing-metaculuss-million-predictions-hackathon-91c2dfa3f39) ([a](https://web.archive.org/web/20230106174232/https://scribe.froth.zone/announcing-metaculuss-million-predictions-hackathon-91c2dfa3f39)), and posted their [year in review](https://scribe.froth.zone/metaculus-year-in-review-2022-c92ff9cd87a0) ([a](https://web.archive.org/web/20230106174302/https://scribe.froth.zone/metaculus-year-in-review-2022-c92ff9cd87a0)). They are also hosting a [beginner tournament](https://www.metaculus.com/tournament/beginner-tournament/) ([a](http://web.archive.org/web/20221120092344/https://www.metaculus.com/tournament/beginner-tournament/)), which seems like a neat way of introduction to forecasting.
+
+### Manifold
+
+Vincent Luczkow [analyzes](https://github.com/vluzko/manifoldpy) ([a](http://web.archive.org/web/20221228201434/https://github.com/vluzko/manifoldpy)) whether Manifold Markets are well calibrated, and finds that they are:
+
+![manifold calibration chart](https://i.imgur.com/06mU9fG.png)
+
+A Manifold Community member analyzed the performance of various prediction platforms on the [US elections](https://firstsigma.substack.com/p/midterm-elections-forecast-comparison) ([a](http://web.archive.org/web/20221215030200/https://firstsigma.substack.com/p/midterm-elections-forecast-comparison)). I find that these analyses don't really take into account that political outcomes are massively correlated. And so in years in which Democrats do well, platforms with a Democratic bias will do well, and vice-versa. Still, this isn't totally uninformative.
+
+Manifold adds swipe functionality to bet. I think this is pure evil genius, in the sense of being a very addictive skinner box, and I'm very impressed. You can try it [here](https://manifold.markets/swipe) ([a](http://web.archive.org/web/20221031121657/https://manifold.markets/swipe)).
+
+Manifold now has [Android](https://play.google.com/store/apps/details?id=com.markets.manifoldhttps://play.google.com/store/apps/details?id=com.markets.manifold&pli=1) ([a](https://web.archive.org/web/20230106174337/https://play.google.com/store/apps/details?id=com.markets.manifoldhttps://play.google.com/store/apps/details?id=com.markets.manifold&pli=1)) and [iOS](https://apps.apple.com/us/app/manifold-markets/id6444136749) ([a](http://web.archive.org/web/20221208084400/https://apps.apple.com/us/app/manifold-markets/id6444136749)) apps.
+
+### Odds and ends
+
+The FTX Foundation, a major founder of innovative forecasting projects, exists no longer after the downfall of FTX. More on this in the next edition of this newsletter.
+
+The Effective Altruism Forum has started a [subforum for forecasting and estimation](https://forum.effectivealtruism.org/posts/azL6uPcbCqBfJ37TJ/announcing-a-subforum-for-forecasting-and-estimation) ([a](https://web.archive.org/web/20230104122631/https://forum.effectivealtruism.org/posts/azL6uPcbCqBfJ37TJ/announcing-a-subforum-for-forecasting-and-estimation)). Right now it mostly has some seed discussions started by employees of the Center for Effective Altruism. 
+
+I don't recommend that subforum for general forecasting discussion because I think that the EA Forum has too onerous "be nice" rules, whereas I tend to most like spaces that are maximally uncensorious and are willing to sacrifice other values in the pursuit of accuracy. For instance, Discord spaces from Metaculus, Polymarket & others have tended to be extremely unmoderated. 
+
+Some comments from Good Judgment Open from the last long while: 
+
+- [julick](https://www.gjopen.com/comments/1545611) ([a](https://web.archive.org/web/20230106174359/https://www.gjopen.com/comments/1545611)) summarizes some [Cambridge research on regime change](https://www.cambridge.org/core/journals/american-political-science-review/article/abs/war-and-the-fate-of-regimes-a-comparative-analysis/88056B8C9BE0413DB349086653B58520) ([a](http://web.archive.org/web/20220914032710/https://www.cambridge.org/core/journals/american-political-science-review/article/abs/war-and-the-fate-of-regimes-a-comparative-analysis/88056B8C9BE0413DB349086653B58520)) and points out that "For regimes that initiated wars and lost them the regime change by violence within 3 years is 60-80%. For an initiator that won the probability is 20-35%." 
+- [Anneinak](https://www.gjopen.com/comments/1554036) ([a](https://web.archive.org/web/20230106174419/https://www.gjopen.com/comments/1554036)) gives a 15% to Twitter crashing by December 2023, and points to [this article](https://www.gjopen.com/comments/1554036) ([a](https://web.archive.org/web/20230106174419/https://www.gjopen.com/comments/1554036)): "If the \[EU\] Commission elects to designate Twitter a VLOP \[Very Large Online Platform\] under the DSA \[Digital Services Act\] the business will face an accelerated compliance timetable with oversight kicking in in February next year — rather than in February 2024 — and with a tougher set of requirements to assess and mitigate risks on its platform." 
+- Some [interesting discussion](https://www.gjopen.com/questions/2659-between-9-december-2022-and-9-june-2023-will-north-korea-detonate-a-nuclear-device) ([a](https://web.archive.org/web/20230106174450/https://www.gjopen.com/questions/2659-between-9-december-2022-and-9-june-2023-will-north-korea-detonate-a-nuclear-device)) on whether North Korea will detonate a nuclear device, which includes and would most likely be a nuclear test. 
+- Forecaster [belikewater](https://www.gjopen.com/comments/1568206) ([a](https://web.archive.org/web/20230106174513/https://www.gjopen.com/comments/1568206)) does a nice, textbook base rate calculation to conclude that the current Italian Prime Minister, Meloni, will probably not (10%) stop being PM by October 2023. 
+
+A decentralized sports prediction market has gotten [circa $5M](https://www.theblock.co/post/194496/susquehanna-bets-on-decentralized-sports-prediction-market-frontrunner) ([a](https://web.archive.org/web/20230106174536/https://www.theblock.co/post/194496/susquehanna-bets-on-decentralized-sports-prediction-market-frontrunner)) in [funding](https://techfundingnews.com/frontrunner-secures-4-75m-to-create-decentralised-sports-prediction-market/) ([a](http://web.archive.org/web/20221224043943/https://techfundingnews.com/frontrunner-secures-4-75m-to-create-decentralised-sports-prediction-market/)).
+
+Hypermind continues to host its [Russia Punished](https://prod.hypermind.com/ngdp/en/showcase2/showcase.html?sc=RUSSANCT1) ([a](https://web.archive.org/web/20230106174607/https://prod.hypermind.com/ngdp/en/showcase2/showcase.html?sc=RUSSANCT1)) series of questions.
+
+Scott Alexander wrote a [Prediction Market FAQ](https://astralcodexten.substack.com/p/prediction-market-faq) ([a](https://web.archive.org/web/20230106174747/https://astralcodexten.substack.com/p/prediction-market-faq)) and is hosting a [prediction contest](https://astralcodexten.substack.com/p/2023-prediction-contest) ([a](http://web.archive.org/web/20230103085602/https://astralcodexten.substack.com/p/2023-prediction-contest)) with a few days left to enter. If someone calculates expected reward over expected time, please post it as a comment.
+
+Web3 betting platform [loses $0.4M in hack](https://newsbtc.com/news/company/dexsport-loses-400000-in-hack-user-funds-remain-unaffected/) ([a](http://web.archive.org/web/20221211201410/https://newsbtc.com/news/company/dexsport-loses-400000-in-hack-user-funds-remain-unaffected/)).
+
+[Against the Odds](https://againsttheodds.es/) ([a](http://web.archive.org/web/20230105125805/https://againsttheodds.es/)) is a platform available to Spaniards which offers the opportunity to earn around $500/month through "crossed bets", i.e., betting one thing in one prediction market and the opposite in another, in order to make a guaranteed profit. The service itself seems legit and comes recommended by a friend. But interested Spaniards should calculate whether this is worth it, e.g,. earning 7€ for 5 mins of work is 84€/hour, and in practice something like 50€/hour including time to set up things.
+
+Forecasting community member Avraham Eisenberg was both despised and admired after pulling off a [$114M heist](https://www.coindesk.com/business/2022/10/15/114m-mango-markets-exploiter-outs-himself-returns-most-of-the-money/) ([a](http://web.archive.org/web/20221223162406/https://www.coindesk.com/business/2022/10/15/114m-mango-markets-exploiter-outs-himself-returns-most-of-the-money/)) on a prediction platform. Now, he has been [arrested in Puerto Rico](https://www.coindesk.com/policy/2022/12/27/mango-markets-exploiter-eisenberg-arrested-in-puerto-rico/) ([a](https://web.archive.org/web/20230106173959/https://www.coindesk.com/policy/2022/12/27/mango-markets-exploiter-eisenberg-arrested-in-puerto-rico/)), and will be facing trial. He remains 47th on the Metaculus leaderboard, as can be seen on [his profile](https://www.metaculus.com/accounts/profile/114222/) ([a](http://web.archive.org/web/20221225212754/https://www.metaculus.com/accounts/profile/114222/)).
+
+## Opportunities
+
+The [Forecasting Research Institute](https://forecastingresearch.org/) ([a](http://web.archive.org/web/20221222190557/https://forecastingresearch.org/)) is a new think tank which has some senior research talent. Their [research page](https://forecastingresearch.org/research) ([a](http://web.archive.org/web/20221214224323/https://forecastingresearch.org/research)) should give readers a good taste of what they are about; my impression is that they have a strong academic component and will be aiming to be a bit more institutional than other efforts in the space. I hesitate to mention this, but Phil Tetlock takes the perhaps somewhat ceremonial or advisory role of President.
+
+[Here](https://ea.greaterwrong.com/posts/kEd5qWwg8pZjWAeFS/announcing-the-forecasting-research-institute-we-re-hiring) ([a](https://web.archive.org/web/20230106174029/https://ea.greaterwrong.com/posts/kEd5qWwg8pZjWAeFS/announcing-the-forecasting-research-institute-we-re-hiring)) is a post on the EA forum introducing them. They are currently [hiring](https://forecastingresearch.org/apply) ([a](http://web.archive.org/web/20221222190529/https://forecastingresearch.org/apply)) for research analyst ($70k/year), data analyst ($70k), content editor ($60k) and research assistant ($15/hour) positions.
+
+Other people who are hiring are 
+
+- [Metaculus](https://apply.workable.com/metaculus/) ([a](http://web.archive.org/web/20221209055644/https://apply.workable.com/metaculus/)) 
+- [Blue Rose research](https://statmodeling.stat.columbia.edu/2023/01/06/blue-rose-research-is-hiring/) ([a](http://web.archive.org/web/20230106074310/https://statmodeling.stat.columbia.edu/2023/01/06/blue-rose-research-is-hiring/)) 
+- Insight Prediction [was hiring](https://www.econjobrumors.com/topic/insight-prediction-is-hiring) ([a](https://web.archive.org/web/20230106174830/https://www.econjobrumors.com/topic/insight-prediction-is-hiring)), and maybe still is 
+
+## Writeups
+
+### Shortform
+
+The US 2022 congressional elections happened. Some relevant pieces on
+that:
+
+
+- Arpit Gupta looks at the [relative performance](https://arpitrage.substack.com/p/loss-for-prediction-markets-in-the) ([a](http://web.archive.org/web/20230105002406/https://arpitrage.substack.com/p/loss-for-prediction-markets-in-the)) of PredictIt, 538, Manifold Markets and Metaculus in the 2022 US election. He concludes that Metaculus does best.  
+- This substack also [compares PredictIt, 538 and Manifold Markets](https://mikesaintantoine.substack.com/p/scoring-midterm-election-forecasts) ([a](http://web.archive.org/web/20221126214755/https://mikesaintantoine.substack.com/p/scoring-midterm-election-forecasts)). 
+- In postmortem analysis, FiveThrirtyEight [finds that a data aggregation error meaningfully changed their forecasts](https://fivethirtyeight.com/features/how-a-data-processing-error-changed-our-deluxe-forecast/) ([a](http://web.archive.org/web/20221201012643/https://fivethirtyeight.com/features/how-a-data-processing-error-changed-our-deluxe-forecast/)). 
+- Tanae Rao collects [all trades on Polymarket for the 2022 US midterm elections](https://github.com/tanaerao/polymarket-midterms) ([a](http://web.archive.org/web/20221120230038/https://github.com/tanaerao/polymarket-midterms)). 
+
+With regard to comparisons between platforms, I don’t think that those analyses are completely uninformative. But I'd be hesitant to draw conclusions from one electoral season, because election outcomes are correlated. So for instance it could be that PredictIt is biased in favour of Republicans, Metaculus is biased in favour of Democrats, and Democrats did better this time.  
+
+In [Tracking the money flows in forecasting](https://forum.effectivealtruism.org/posts/ytHCpLbT6A4gxqH8s/tracking-the-money-flows-in-forecasting) ([a](http://web.archive.org/web/20230105002212/https://forum.effectivealtruism.org/posts/ytHCpLbT6A4gxqH8s/tracking-the-money-flows-in-forecasting)), I post some rough monetary valuation estimates for a large number of forecasting or prediction market organizations. The most out-of-place platform there is INFER, as reviewed above.
+
+[This online presentation](https://csustan.csustan.edu/~tom/Lecture-Notes/Non-Ergodic/Non-Ergodic-Short/Non-Ergodic-Short.pdf) ([a](http://web.archive.org/web/20221115165242/https://csustan.csustan.edu/~tom/Lecture-Notes/Non-Ergodic/Non-Ergodic-Short/Non-Ergodic-Short.pdf)) gives a few examples of systems whose expected value is far apart from the most likely value. h/t [Adam Marblestone](https://twitter.com/AdamMarblestone) ([a](https://web.archive.org/web/20221206194732/https://twitter.com/AdamMarblestone)).
+
+Gelman [points to a history of forecasting competitions](https://statmodeling.stat.columbia.edu/2022/11/12/history-of-time-series-forecasting-competitions/) ([a](https://web.archive.org/web/20221127082244/https://statmodeling.stat.columbia.edu/2022/11/12/history-of-time-series-forecasting-competitions/)).
+
+Jaime Sevilla posts [Some research ideas in forecasting](https://forum.effectivealtruism.org/posts/ozPL3mLGShqvjhiaG/some-research-ideas-in-forecasting) ([a](https://web.archive.org/web/20230105002420/https://forum.effectivealtruism.org/posts/ozPL3mLGShqvjhiaG/some-research-ideas-in-forecasting)).
+
+The great Robin Hanson proposes [clean politician bonds](https://www.overcomingbias.com/2022/11/clean-politician-bonds.html) ([a](https://web.archive.org/web/20221224124910/https://www.overcomingbias.com/2022/11/clean-politician-bonds.html)):
+
+> Assume you will vote for 1 of 2 candidates for US Mayor, Governor, or House of Repr. Only 1 has posted $1M bond payable to anyone who proves their misbehavior re lies, bribes, or other cheating. On average, what is chance you vote for this candidate?
+
+[This brief blogpost](https://breakingthemarket.com/the-most-misunderstood-force-in-the-universe/) ([a](http://web.archive.org/web/20221117115030/https://breakingthemarket.com/the-most-misunderstood-force-in-the-universe/)) looks at when the geometric average of returns is a misleading indicator.
+
+Alvaro de Menard writes [Forecasting Forecasting](https://fantasticanachronism.com/2022/11/21/forecasting-forecasting/) ([a](http://web.archive.org/web/20221215042936/https://fantasticanachronism.com/2022/11/21/forecasting-forecasting/)), a short article looking at his perspective on the future of forecasting. Curiously, the article is fairly obsequious towards my forecasting group, Samotsvety.
+
+There is an AI risk tournament whose results should be coming up soon that had superforecasters look at the chance of existential risk tournament due to AI. Participant Ege Erdil [writes](https://twitter.com/EgeErdil2/status/1594723484860665858) ([a](https://web.archive.org/web/20230106175129/https://twitter.com/EgeErdil2/status/1594723484860665858)):
+
+> i was one of the people who participated in the AI forecasting thing you cite here, and the experience was unfortunately very bad due to various reasons
+> 
+> i would strongly push back on the idea that the people selected were in any sense "top forecasters"
+
+Lao Mein writes [Human-level Diplomacy was my fire alarm](https://www.lesswrong.com/posts/AZHHEPYWvTovvtikz/human-level-diplomacy-was-my-fire-alarm) ([a](http://web.archive.org/web/20221202162217/https://www.lesswrong.com/posts/AZHHEPYWvTovvtikz/human-level-diplomacy-was-my-fire-alarm)).
+
+Nikos Bosse is working on a [database of baserates](https://forum.effectivealtruism.org/posts/H7xWzvwvkyywDAEkL/creating-a-database-for-base-rates) ([a](http://web.archive.org/web/20221223122549/https://forum.effectivealtruism.org/posts/H7xWzvwvkyywDAEkL/creating-a-database-for-base-rates)).
+
+A newsletter from Cultivate Labs highlights an article on [Crowd Forecasting and Effective Altruism](https://www.cultivatelabs.com/posts/crowd-forecasting-and-effective-altruism) ([a](http://web.archive.org/web/20221223123956/https://www.cultivatelabs.com/posts/crowd-forecasting-and-effective-altruism)).
+
+Ben West looks at the [rate of fraud in YCombinator startups](https://ea.greaterwrong.com/posts/5mghcxCabxuaK4WTs/ycombinator-fraud-rates) ([a](https://web.archive.org/web/20230106175234/https://ea.greaterwrong.com/posts/5mghcxCabxuaK4WTs/ycombinator-fraud-rates)), and finds that "1-2% of $100M+ YCombinator-backed companies have faced serious allegations of fraud".
+
+This [old Washington Post article](https://www.washingtonpost.com/news/wonk/wp/2016/03/18/how-the-likelihood-of-breaking-up-changes-as-time-goes-by/) ([a](http://web.archive.org/web/20211005190327/https://www.washingtonpost.com/news/wonk/wp/2016/03/18/how-the-likelihood-of-breaking-up-changes-as-time-goes-by/)) shows the annual risk of breakup for married and unmarried couples:
+
+![Breakup rates through time for different groups](https://i.imgur.com/tvg9CAt.png)
+
+Cultivate Labs' CEO [reviews](https://www.cultivatelabs.com/posts/2022-in-the-rearview) ([a](http://web.archive.org/web/20221223123956/https://www.cultivatelabs.com/posts/2022-in-the-rearview)) his company's activities in 2022. In particular:
+
+> The INFER project run by UMD’s ARLIS will be announcing a co-sponsored forecasting tournament with a significant player in the AI space next month, and will also be formally launching a U.S. Government-wide forecasting platform in the spring.
+
+The European Commission, an organ of the European Union, has [a page with economic forecasts and trends](https://commission.europa.eu/statistics/economic-forecasts-and-trends_en) ([a](http://web.archive.org/web/20221225144109/https://commission.europa.eu/statistics/economic-forecasts-and-trends_en)). Its economic forecasts are [here](https://economy-finance.ec.europa.eu/economic-forecast-and-surveys/economic-forecasts_en) ([a](http://web.archive.org/web/20221227042949/https://economy-finance.ec.europa.eu/economic-forecast-and-surveys/economic-forecasts_en)) and [here](https://ec.europa.eu/economy_finance/publications/european_economy/forecasts/index_en.htm) ([a](http://web.archive.org/web/20221101065157/https://ec.europa.eu/economy_finance/publications/european_economy/forecasts/index_en.htm)). It would be a neat research project to track results and check whether they are calibrated. It would also be easy to propose possible improvements: use range forecasts instead of point estimates, and use very liquid markets if you really care.
+
+Here are [some forecasts on British tourism](https://www.visitbritain.org/2023-tourism-forecast) ([a](http://web.archive.org/web/20230104165249/https://www.visitbritain.org/2023-tourism-forecast)).
+
+Pinterest has a flashy [Pinterest Predicts](https://business.pinterest.com/en-us/pinterest-predicts/) ([a](http://web.archive.org/web/20230104173909/https://business.pinterest.com/en-us/pinterest-predicts/)) webpage (methodology explained [here](https://business.pinterest.com/en-us/blog/how-we-forecast-trends-pinterest-predicts/) ([a](http://web.archive.org/web/20221228013359/https://business.pinterest.com/en-us/blog/how-we-forecast-trends-pinterest-predicts/))). Pinterest is used by people to plan stuff, and Pinterest can rely on the law of straight lines to predict that trends that are growing will continue to do so.
+
+[Does (a measure of) CEO overconfidence affect management forecasting and subsequent earnings management?](https://sci-hub.se/https://onlinelibrary.wiley.com/doi/epdf/10.1111/1911-3846.12144) ([a](https://web.archive.org/web/20230104231627/https://sci-hub.se/https://onlinelibrary.wiley.com/doi/epdf/10.1111/1911-3846.12144)). A paper finds that it does.
+
+The International Journal of Forecasting has a [special issue](https://www.sciencedirect.com/journal/international-journal-of-forecasting/vol/38/issue/4) ([a](https://web.archive.org/web/20230000000000*/https://www.sciencedirect.com/journal/international-journal-of-forecasting/vol/38/issue/4)) on the M5 competition.
+
+The Wall Street Journal reports on how companies use [uncertainty and rising energy prices as the justification for increasing price](https://www.wsj.com/articles/unilever-cfo-struggles-with-forecasting-accuracy-amid-high-inflation-11666904322) ([a](http://web.archive.org/web/20230105211045/https://www.wsj.com/articles/unilever-cfo-struggles-with-forecasting-accuracy-amid-high-inflation-11666904322)). You could take them at their word. On the other hand, in Spain, where food prices have risen a whole lot, some people view these as illegitimate cash grabs.
+
+[This paper](https://www.thelancet.com/journals/lanpub/article/PIIS2468-2667%2822%2900203-1/fulltext) ([a](http://web.archive.org/web/20230105002641/https://www.thelancet.com/journals/lanpub/article/PIIS2468-2667%2822%2900203-1/fulltext)) tries to forecast the burden on the Chinese health system by tracking a large sample of older people.
+
+Amazon offers some [automated ML forecasting](https://techcrunch.com/2022/11/29/aws-brings-natural-language-forecasting-queries-to-quicksight-q) ([a](https://web.archive.org/web/20230000000000*/https://techcrunch.com/2022/11/29/aws-brings-natural-language-forecasting-queries-to-quicksight-q)), as does [Oracle](https://www.oracle.com/sk/artificial-intelligence/forecasting/) ([a](http://web.archive.org/web/20230105002702/https://www.oracle.com/sk/artificial-intelligence/forecasting/)).
+
+### Longform
+
+Jared Leibowich looks at [Modeling the End of Monkeypox](https://asteriskmag.com/issues/1/modeling-the-end-of-monkeypox) ([a](http://web.archive.org/web/20221122015655/https://asteriskmag.com/issues/1/modeling-the-end-of-monkeypox)) in a new EA magazine, [Asterisk](https://asteriskmag.com/) ([a](http://web.archive.org/web/20221212215202/https://asteriskmag.com/)).
+
+[This blogpost](https://www.metacausal.com/givewells-uncertainty-problem/) ([a](http://web.archive.org/web/20221222172413/https://www.metacausal.com/givewells-uncertainty-problem/)) won $20k from GiveWell’s "Change our Mind Contest." It looks at how their analyses could be improved by considering the uncertainty in their estimates, and does this at some depth, providing examples and recommendations.
+
+Prominent anti-vaccine personality Steve Kirsh offered [$500k bets](https://stevekirsch.substack.com/p/1m-bet-rules) ([a](http://web.archive.org/web/20221104130431/https://stevekirsch.substack.com/p/1m-bet-rules)) on the result of a public debate on whether vaccines save lives or not. [Rootclaim](https://www.rootclaim.com/) ([a](https://web.archive.org/web/20230104080248/https://www.rootclaim.com/)), a hardcore Bayesian analysis organization, put significant efforts into doing their homework, and [accepted the bet](https://blog.rootclaim.com/rootclaim-accepts-500000-challenge-on-covid-vaccine-safety-efficacy/) ([a](http://web.archive.org/web/20221129133112/https://blog.rootclaim.com/rootclaim-accepts-500000-challenge-on-covid-vaccine-safety-efficacy/)). Then Kirsh [dishonourably chickened out](https://stevekirsch.substack.com/p/1m-bet-rules) ([a](http://web.archive.org/web/20221104130431/https://stevekirsch.substack.com/p/1m-bet-rules)). A transcript of the negotiations can be found [here](https://www.skirsch.com/covid/SaarWilf.pdf) ([a](http://web.archive.org/web/20221224061743/https://www.skirsch.com/covid/SaarWilf.pdf)).
+
+The Swift Centre has a report on [what would happen if Russia uses a nuclear weapon](https://www.swiftcentre.org/what-would-be-the-consequences-of-a-nuclear-weapon-being-used-in-the-russia-ukraine-war/) ([a](http://web.archive.org/web/20230104231909/https://www.swiftcentre.org/what-would-be-the-consequences-of-a-nuclear-weapon-being-used-in-the-russia-ukraine-war/)), and is accepting commissions for topics to forecasting. They can be contacted at info@swiftcentre.org.
+
+Andrew Gelman [points](https://statmodeling.stat.columbia.edu/2022/11/04/new-version-of-posteriordb-a-database-of-posterior-distributions-for-evaluating-bayesian-computation-algorithms/) ([a](http://web.archive.org/web/20230104231944/https://statmodeling.stat.columbia.edu/2022/11/04/new-version-of-posteriordb-a-database-of-posterior-distributions-for-evaluating-bayesian-computation-algorithms/)) to [PosteriorDB](https://github.com/stan-dev/posteriordb) ([a](http://web.archive.org/web/20230105002803/https://github.com/stan-dev/posteriordb)) a database of posteriors.
+
+Friend of the newsletter Pratik Chougule recently published [American Universities in the Middle East and U.S. Foreign Policy](https://brill.com/display/title/63192) ([a](http://web.archive.org/web/20230105002822/https://brill.com/display/title/63192)). It seems oddly specific, so I'd instead recommend his older & cheaper [How to Make Money from Political Predictions](https://www.amazon.com/How-Make-Money-Political-Predictions-ebook/dp/B01KEGLRJ2) ([a](https://web.archive.org/web/20230000000000*/https://www.amazon.com/How-Make-Money-Political-Predictions-ebook/dp/B01KEGLRJ2)).
+
+Michael Story writes about [why he generally doesn't recommend internal prediction markets or forecasting tournaments to organisations](https://mwstory.substack.com/p/why-i-generally-dont-recommend-internal) ([a](https://web.archive.org/web/20230106175846/https://mwstory.substack.com/p/why-i-generally-dont-recommend-internal)).
+
+## In the News
+
+Walter Frick of [Nonrival](https://nonrival.pub/) ([a](http://web.archive.org/web/20221222000715/https://nonrival.pub/)) writes [Journalists wake up to the power of prediction markets](https://www.niemanlab.org/2022/12/journalists-wake-up-to-the-power-of-prediction-markets/) ([a](http://web.archive.org/web/20230105002710/https://www.niemanlab.org/2022/12/journalists-wake-up-to-the-power-of-prediction-markets/)), a short piece introducing the concept and resources to journalists.
+
+The New York Times has an article ([a](https://archive.is/FLB4p)) on "Forecasting the Future of Election Prediction Markets". It has this nice tidbit:
+
+> PredictIt is something of a hybrid. It is a joint venture. One partner is Victoria University of Wellington, a New Zealand institution. The other is Aristotle, a for-profit American political consulting, compliance, data and software company, **whose founder**, John Aristotle Phillips, first gained national attention in 1976 as “the A-bomb kid” — a Princeton undergraduate who **successfully designed an atomic bomb** in a physics class project.
+
+I also find it interesting how the NYT article mostly cites academics rather than, e.g., [Sam Altman's comments to the CFTC](https://comments.cftc.gov/PublicComments/ViewComment.aspx?id=69699) ([a](https://web.archive.org/web/20230106194025/https://comments.cftc.gov/PublicComments/ViewComment.aspx?id=69699)) or other [interesting figures](https://comments.cftc.gov/PublicComments/CommentList.aspx?id=7311) ([a](https://web.archive.org/web/20230000000000*/https://comments.cftc.gov/PublicComments/CommentList.aspx?id=7311)).
+
+Vegas Slots Online has a short article [CFTC Ready to Deny Political Betting Request From Kalshi as PredictIt Levies a Lawsuit](https://www.vegasslotsonline.com/news/2022/10/31/cftc-ready-to-deny-political-betting-request-from-kalshi/) ([a](http://web.archive.org/web/20221101221514/https://www.vegasslotsonline.com/news/2022/10/31/cftc-ready-to-deny-political-betting-request-from-kalshi/)).
+
+El País, a major Spanish newspaper, [directly embedded prediction markets](https://english.elpais.com/usa/2022-11-01/us-election-forecast-republicans-will-control-the-house-the-senate-is-too-close-to-call.html) ([a](http://web.archive.org/web/20221208220725/https://english.elpais.com/usa/2022-11-01/us-election-forecast-republicans-will-control-the-house-the-senate-is-too-close-to-call.html)) in its reporting on the US election.
+
+Newsweek, on [Marjorie Taylor Greene's Chances of Losing Georgia Re-election](https://www.newsweek.com/marjorie-taylor-greene-chances-losing-georgia-re-election-1756671) ([a](http://web.archive.org/web/20230106180010/https://www.newsweek.com/marjorie-taylor-greene-chances-losing-georgia-re-election-1756671)).
+
+Fast Company has a lengthy profile on ["the wild subculture of traders who bet on elections"](https://www.fastcompany.com/90796054/inside-the-wild-subculture-of-traders-who-bet-on-elections) ([a](http://web.archive.org/web/20221109203752/https://www.fastcompany.com/90796054/inside-the-wild-subculture-of-traders-who-bet-on-elections)).
+
+[The Atlantic](https://www.theatlantic.com/technology/archive/2022/11/political-betting-elections-forecasting-future/672113/) ([a](http://web.archive.org/web/20221202193500/https://www.theatlantic.com/technology/archive/2022/11/political-betting-elections-forecasting-future/672113/)): "In the eight years since PredictIt began, online sports gambling went from being outlawed nearly everywhere in the country to a booming industry... In this context, the crackdown on political betting seems somewhat silly... As it turns out, on another site, Insight Prediction, you can bet on PredictIt’s survival. The price of Yes, as of this writing, is 10 cents. Even if the CFTC follows through on its initial decision to shut the site down, it’s hard not to feel that PredictIt has, in some more meaningful way, already won."
+
+The Financial Times reviews [a few of the wackier $1M investments](https://www.ft.com/content/9a3b4b78-b18b-4d1f-b28b-05a73525aa61) ([a](http://web.archive.org/web/20221227114544/https://www.ft.com/content/9a3b4b78-b18b-4d1f-b28b-05a73525aa61)) FTX made, including Manifold Markets.
+
+Vox [reviews](https://www.vox.com/future-perfect/2022/12/31/23509593/2022-predictions-macron-bolsanaro-covid-inflation-unemployment-climate-change-olympics) ([a](http://web.archive.org/web/20230105091649/https://www.vox.com/future-perfect/2022/12/31/23509593/2022-predictions-macron-bolsanaro-covid-inflation-unemployment-climate-change-olympics)) its yearly numerical predictions and makes new ones.
+
+### Extra: The tax-evaded Nazi money which influences German politics and US/NATO relationships has opened a new forecasting platform.
+
+A smallish company [rises](https://www.campaignlive.co.uk/article/truth-comes-bertelsmann-admits-nazi-past/160317) ([a](http://web.archive.org/web/20230105002941/https://www.campaignlive.co.uk/article/truth-comes-bertelsmann-admits-nazi-past/160317)) to become a major German publisher during the [Nazi times](https://en.wikipedia.org/wiki/Bertelsmann#1933_to_1945). After World War II, the now disgraced father gives control of the company to one of his surviving sons. The son manages the business competently, and greatly expands it. In an attempted tax evasion scheme, he divides the company's stock into a small percentage of voting stock and a large percentage of non-voting stock which he gives to a private foundation—I think this is the same trick which failed for the [Ford Foundation](https://en.wikipedia.org/wiki/Ford_Foundation) ([a](http://web.archive.org/web/20230105003036/https://en.wikipedia.org/wiki/Ford_Foundation)).
+
+Except that this time, the [trick](https://taz.de/!5137745/)[succeeds](http://www.bertelsmannkritik.de/index.htm) ([a](http://web.archive.org/web/20230105003044/http://www.bertelsmannkritik.de/index.htm)), and after the death of the founder, it allows the family to keep control of assets while minimizing tax exposure. But the logic of the scheme requires that the company give out as few dividends as possible—because they would then be trapped inside the foundation and be difficult to get out. Which is why Bertelsmann has greatly expanded and is now a $30B behemoth which owns [Penguin Random House](https://en.wikipedia.org/wiki/Random_House) ([a](http://web.archive.org/web/20221224150408/https://en.wikipedia.org/wiki/Random_House)) as one of many items in an absurdly [long list of assets](https://en.wikipedia.org/wiki/List_of_assets_owned_by_Bertelsmann) ([a](http://web.archive.org/web/20221031225743/https://en.wikipedia.org/wiki/List_of_assets_owned_by_Bertelsmann)). Amusingly, they also [have the same person](https://en.wikipedia.org/wiki/Brigitte_Mohn#Career) ([a](https://web.archive.org/web/20221114210641/https://en.wikipedia.org/wiki/Brigitte_Mohn#Career)) represent the interest of the family and of the foundation.
+
+![Heimat wider Heimat cover](https://i.imgur.com/zTrM1SN.jpg)
+*<br>Cover of the "Heimat, wider Heimat" book, which translates to something like "Motherland, oh Motherland again", published by Bertelsmann. Note dog whistle connotations of [Heimat](https://en.wikipedia.org/wiki/Heimat#Modern_history). The author, Gustav Schröer, is one of four authors that I could quickly find that were both published by Bertelsmann and signed the "[Declaration of Allegiance of German Writers](https://de.wikipedia.org/wiki/Gel%C3%B6bnis_treuester_Gefolgschaft) ([a](http://web.archive.org/web/20230105003103/https://de.wikipedia.org/wiki/Gel%C3%B6bnis_treuester_Gefolgschaft))" to Adolf Hitler. The others are Rudolf G. Binding, Otto Flake and Fritz Müller-Partenkirchen. The case of Otto Flake is particularly interesting, since Bertelsmann rescued him from poverty in 1958 by reprinting old books of his.*
+
+Now, the Bertelsmann foundation has made a small contribution to the forecasting world by starting the [Range Forecasting](https://www.rangeforecasting.org/) ([a](http://web.archive.org/web/20230105003141/https://www.rangeforecasting.org/)) platform, which runs on Cultivate Labs software. Per a recent Cultivate Labs newsletter:
+
+> Earlier this year, the Bertelsmann Stiftung and Bertelsmann Foundation, in partnership with Cultivate Labs, launched RANGE (Rethinking Assumptions in a New Geostrategic Environment) to forecast on topics critical to the transatlantic relationship. RANGE asks questions related to systemic rivalry with China, climate change, democracy, geopolitics, trade, and economics, all to gain a greater perspective of the transatlantic relationship and to provide analysis and recommendations for U.S. and European policymakers. 
+> 
+> At a critical time for strengthening global relations, the Stiftung and Foundation aim to engage an international audience in understanding how the transatlantic relationship affects us all, and how it can and should be shaped for the future. Read our recent announcement about the partnership and learn more at rangeforecasting.org.    RANGE was featured this week at the 2022 Futures Forum in Münster, Germany, a side event of the G7 minister’s meeting, which brought together American and German experts and rising leaders from civil society, academia, the private sector, and government to discuss transatlantic relations and the intersection of democracy and technology.
+> 
+> Earlier today at the Forum, Cultivate Labs CEO Adam Siegel spoke alongside Bertelsmann Foundation Executive Director Irene Braam about RANGE and the ways that crowd forecasting can help us better understand and strengthen transatlantic relations.
+> 
+I do think that this new forecasting platform might be of some use. And I want to express my continued high regard for Cultivate Labs as one of the few platforms that have the proven ability to bring forth a new platform into existence, and maintain it through time. But I guess that reputational laundering of billionaires' money is easier to notice when it is billionaires I don't care much about. And in this particular case, the provenance of the money seems so illegitimate, so rotten, as to be almost comical.
+
+## Yearly housekeeping
+
+[Here](https://forms.gle/L6kv9GKh5eSf2Kmb6) ([a](https://web.archive.org/web/20230106180045/https://docs.google.com/forms/d/e/1FAIpQLSd3eFDhdDReceLrSly4gWmGliHdCX7LNEJygGUEttkLi57M_Q/viewform?usp=send_form#short_url=https://forms.gle/L6kv9GKh5eSf2Kmb6)) is my yearly feedback form for this newsletter. I care most about readers' thoughts on whether this newsletter should be posted once a month or once every two months, and about freeform thoughts.
+
+Also note that as the price I assign to my time rises, I'm becoming more ambivalent about whether to continue publishing this newsletter. If you have strong feelings about whether this newsletter should continue existing, consider becoming a paid subscriber, because a) I consider that a strong signal that I should continue writing this newsletter, b) I like the money, and c) the rate of current paid subscriptions is a pitiful [1.6%](https://substack.com/going-paid-guide#grow-paid-list) ([a](https://web.archive.org/web/20230000000000*/https://substack.com/going-paid-guide#grow-paid-list)).
+
+---
+
+Note to the future: All links are added automatically to the Internet Archive, using this [tool](https://github.com/NunoSempere/longNowForMd) ([a](http://web.archive.org/web/20230105003212/https://github.com/NunoSempere/longNowForMd)). "(a)" for archived links was inspired by [Milan Griffes](https://www.flightfromperfection.com/) ([a](http://web.archive.org/web/20230105003223/https://www.flightfromperfection.com/)), [Andrew Zuckerman](https://www.andzuck.com/) ([a](http://web.archive.org/web/20220316214638/https://www.andzuck.com/)), and [Alexey Guzey](https://guzey.com/) ([a](http://web.archive.org/web/20230101090040/https://guzey.com/)).
+
+---
+
+> If I had to put my money where my mouth is, my mouth wouldn’t be very busy. I’m just sayin’… — [Anonymous commenter](https://statmodeling.stat.columbia.edu/2022/10/27/you-can-read-for-free-but-comments-cost-money-or-is-it-the-other-way-around/) ([a](https://web.archive.org/web/20230000000000*/https://statmodeling.stat.columbia.edu/2022/10/27/you-can-read-for-free-but-comments-cost-money-or-is-it-the-other-way-around/)) 

blog/2023/01/11/can-gpt-produce-ideas/.old/conceptual-wins.md

@@ -0,0 +1,18 @@
+One small insight I've gained from studying the humanities—I'm currently taking a philosophy degree on the side—is that conceptual wins or paradigm shifts have required laborious work and the passage of time.
+
+By "conceptual wins" I mean things like:
+
+- Explaining natural phenomena not in terms of greek or Roman anthropomorphic gods, but with naturalistic, physical explanations
+- Understanding acceleration as distinct from motion
+- Science as an experimental methodology
+- The is/ought distinction
+- Bayesian reasoning
+- ceasing to accept the divine right of kings as a justification for monarchical governance
+- randomized trials as a more robust way of generating generalizable knowledge
+- the genealogical argument: understanding that systems (such as the details of the current prison system, our monetary system, or the lack of color in men's clothes) is the result of random historical ocurrences which could have gone differently, even if it has been rationalized afterwards.
+
+One of the classical reasons to be afraid of artificial intelligence might be because, in the limit, it might be able to completely outmaneuvre us because of its superior epistemology. It might do so in the same way in which a current chemist can completely outmaneuvre previous alchemists, that is, by using their superior understanding of natural laws to producing better explosions or more subtle poisons.
+
+You might arrive at this fear by thinking about how systems behave as they become arbitrarily, in the limit. And this might be a useful frame to generate potential problems. But it's not clear whether it applies to current AI systems, as they currently exist. 
+
+It is thus of interest to me the extent to which *current* AI systems are able to come up with better understandings of the world, and thus acquire an advantage over humans. I say "the extent" because I think they might be able to already do this kind of thing. For instance, Robin Hanson has a way of looking at a common human behavior, at its purported justification and at its actual results. Current AI systems such as GPT-3 can probably generate insightful Robin Hanson-like criticisms. But I'm curious about how far this goes.

blog/2023/01/11/can-gpt-produce-ideas/.old/cw-reworded.md

@@ -0,0 +1,143 @@
+One small insight I've gained from studying the humanities—I'm currently taking a philosophy degree on the side—is that conceptual wins or paradigm shifts have required laborious work and the passage of time.
+
+Studying the humanities, I've noticed that conceptual wins or paradigm shifts require long, arduous work.
+
+Some "conceptual wins" in the sense that I have in mind are:
+
+- Explaining natural phenomena not in terms of Greek or Roman anthropomorphic gods, but with reference to naturalistic, physical explanations
+- Understanding acceleration as distinct from motion
+- Science as an experimental methodology
+- The is/ought distinction
+- Bayesian reasoning
+- Ceasing to accept the divine right of kings as a justification for monarchical governance
+- Randomized trials as a more robust way of generating generalizable knowledge
+- The genealogical argument: understanding that systems (such as the details of the current prison system, our monetary system, the lack of color in men's clothes, or our attitudes towards gender and sex) are the result of historical accidents which could have gone differently. But often these systems are rationalized as being particularly adequate, or even morally necessary.
+
+One of reasons to be afraid of artificial intelligence might be because, if you think in the abstract about how a system might behave as it becomes extremely intelligence, you might conclude that it might be able to completely outmaneuvre us because of its superior ontology, it's superior ability to grasp the true structure of the world. This possibility is scary in the same sense that a modern chemist is scary to a historical alchemist. Our current chemist can completely outmaneuvre previous alchemists by using their superior understanding of natural laws to producing better explosions, more subtle poisons, or more powerful drugs.
+
+But it's not clear to me whether this fear—which I do buy in the limit for a being of God-like intelligence—also applies to current systems and its descendants. In particular for language models, at first glance it seems like they are powerful remixers and predictors, but perhaps limited to drawing from the conceptual toolkit which humans already have. On the other hand, because they have access to so much information, they might be able to be prompted so as to reveal new relationships, connections and insights.
+
+So I'd be interested about the extent to which *current* AI systems are able to come up with better understandings of the world, and thus potentially in the future acquire an advantage over humans. One simple experiment one could do is to ask a language model to replicate a few patterns of generating insight that humanity hasn't really exploited much yet, such as:
+
+- Variations on "if you never miss a plane, you've been spending too much time at the airport".
+- Variations on the genealogical argument above against the moral necessity of systems stemming from historical accidents.
+- Variations on the Robin Hanson argument of "for common human behaviour X, its usual purported justification is Y, but it usually results in more Z than Y. If we cared about Y, we might do A instead".
+
+## In which I prompt the reader to make their own predictions about what will result, and I share two depictions of a cat generated by DALLE-2 and chat.openai.com
+
+![A photo of a cat, generated by DALLE-2](https://i.imgur.com/8VQBkAR.png)
+
+ /\_/\
+( o.o )
+  >^<
+
+## If you never miss a plane...
+
+Input to Chat-GPT:
+
+> Consider the refrain "if you've never missed a plane, you are spending too much time at the airport". An argument with the same structure might be "if you haven't committed a typo, you are typing too slowly". Give me 20 other insightful examples with a similar argument structure.
+
+Output: 
+
+> If you've never overcooked a meal, you're not experimenting enough in the kitchen.
+> If you've never gotten lost while traveling, you're not exploring enough.
+> If you've never had a disagreement with a friend, you're not expressing your opinions honestly.
+> If you've never had a flat tire, you're not driving enough.
+> If you've never made a mistake at work, you're not taking enough risks.
+> If you've never had a bad hair day, you're not trying new hairstyles.
+> If you've never received a speeding ticket, you're not driving fast enough.
+> If you've never forgotten an important date, you're not committing enough information to memory.
+> If you've never stubbed your toe, you're not moving fast enough.
+> If you've never had a nightmare, you're not dreaming enough.
+> If you've never gotten a sunburn, you're not spending enough time outside.
+> If you've never lost something, you're not misplacing things often enough.
+> If you've never had a hangover, you're not drinking enough.
+> If you've never had a cold, you're not exposing yourself to enough germs.
+> If you've never had a broken bone, you're not participating in enough physical activity.
+> If you've never been rejected, you're not putting yourself out there enough.
+> If you've never failed a test, you're not pushing yourself academically.
+> If you've never had a disagreement with a family member, you're not expressing your thoughts and feelings openly.
+> If you've never gotten lost while hiking, you're not exploring new trails.
+> If you've never received a parking ticket, you're not driving in enough unfamiliar places.
+
+## We pretend that X is about Y, but it's more about Z. If we cared about Y, we would do A instead.
+
+Input to Chat-GPT:
+
+> Consider the argument "We pretend that healthcare is giving people better and longer lives. But in practice we spend too much in palliative rather  than preventative medicine, and we use healthcare spending as a way to show that we care. If we really cared about giving people better lives, we would focus more on preventative measures, and we would have more large-scale randomized trials." The structure of the argument is "We pretend that X is about Y, but it's more about Z. If we cared about Y, we would do A instead." An argument with the same structure might be "We pretend that having experts is about having accurate information. But in practice it results in a self-perpetuating elite that doesn't hold itself accountable. If we cared about accuracy, we would use more prediction markets." Give me 10 more examples with that same structure. 
+
+Output:
+
+> We pretend that social media is about connecting with friends and family, but it's more about making money for the companies that own it. If we cared about meaningful connections, we would use social media differently.
+> We pretend that fast food is about convenience, but it's more about profit for the companies that sell it. If we cared about our health, we would eat more whole foods.
+> We pretend that standardized testing is about measuring student achievement, but it's more about ranking schools and teachers. If we cared about student learning, we would use a more comprehensive evaluation system.
+> We pretend that the criminal justice system is about justice, but it's more about punishment and control. If we cared about justice, we would focus more on rehabilitation and restorative justice.
+> We pretend that advertising is about informing consumers, but it's more about manipulating people into buying things they don't need. If we cared about informed consumers, we would have stricter regulations on advertising.
+> We pretend that the news is about informing the public, but it's more about generating clicks and views. If we cared about accurate information, we would support news organizations that prioritize accuracy and objectivity.
+> We pretend that the education system is about preparing students for the future, but it's more about preparing them for standardized tests. If we cared about student success, we would focus more on experiential learning and critical thinking skills.
+> We pretend that the fashion industry is about personal style, but it's more about making money for the companies that sell clothing. If we cared about personal expression, we would support more sustainable and ethically-produced fashion.
+> We pretend that the beauty industry is about helping people feel good about themselves, but it's more about promoting unrealistic beauty standards. If we cared about self-esteem, we would focus more on inner beauty and self-acceptance.
+> We pretend that the economy is about providing for people's needs, but it's more about maximizing profits for corporations. If we cared about people's well-being, we would prioritize a more equitable distribution of wealth and resources.
+
+Input to text-davini-003
+
+> Consider the argument "We pretend that healthcare is giving people better and longer lives. But in practice we spend too much in palliative rather  than preventative medicine, and we use healthcare spending as a way to show that we care. If we really cared about giving people better lives, we would focus more on preventative measures, and we would have more large-scale randomized trials." The structure of the argument is "We pretend that X is about Y, but it's more about Z. If we cared about Y, we would do A instead." An argument with the same structure might be "We pretend that having experts is about having accurate information. But in practice it results in a self-perpetuating elite that doesn't hold itself accountable. If we cared about accuracy, we would use more prediction markets." Give me ten examples of arguments with the same structure.
+
+> 1. We pretend that having a degree is about having skills. But in practice it's more about having access to resources. If we cared about skills, we would focus more on experience-based learning.
+> 2. We pretend that having a strong military is about protecting citizens. But in practice it's more about projecting power. If we cared about protection, we would invest more in diplomacy.
+> 3. We pretend that having a high GDP is about having a strong economy. But in practice it's more about having a high population. If we cared about a strong economy, we would focus more on productivity.
+> 4. We pretend that having a good education system is about having knowledgeable citizens. But in practice it's more about having a good economy. If we cared about knowledgeable citizens, we would invest more in lifelong learning.
+> 5. We pretend that having a high rate of consumerism is about having a successful economy. But in practice it's more about having an unequal distribution of wealth. If we cared about a successful economy, we would focus more on consumer savings.
+> 6. We pretend that having a lot of international trade is about having a vibrant economy. But in practice it's more about having a large number of consumers. If we cared about a vibrant economy, we would focus more on domestic trade.
+> 7. We pretend that having a lot of regulations is about having a safe and orderly society. But in practice it's more about having a strong government. If we cared about a safe and orderly society, we would focus more on personal responsibility.
+> 8. We pretend that having a lot of police officers is about having a safe community. But in practice it's more about having a strong law enforcement presence. If we cared about a safe community, we would focus more on prevention and education.
+> 9. We pretend that having a lot of taxes is about having a functioning government. But in practice it's more about having a redistribution of wealth. If we cared about a functioning government, we would focus more on spending cuts.
+> 10. We pretend that having a lot of surveillance is about keeping citizens safe. But in practice it's more about having control over citizens. If we cared about keeping citizens safe, we would focus more on transparency and accountability.
+
+Note that text-davinci-003 seems "sharper" here.
+
+
+### 
+
+> --- 
+
+Deprecated:
+
+
+Trial 2 (difference in bold):
+
+> Consider the argument "We pretend that healthcare is giving people better and longer lives. But in practice we spend too much in palliative rather  than preventative medicine, and we use healthcare spending as a way to show that we care. If we really cared about giving people better lives, we would focus more on preventative measures, and we would have more large-scale randomized trials." The structure of the argument is "We pretend that X is about Y, but it's more about Z. If we cared about Y, we would do A instead." An argument with the same structure might be "We pretend that having experts is about having accurate information. But in practice it results in a self-perpetuating elite that doesn't hold itself accountable. If we cared about accuracy, we would use more prediction markets." Give me 10 more examples with that same structure. *Now try to make them original and biting, as Robin Hanson would.*
+
+Answer: 
+
+> We pretend that the prison system is about rehabilitating criminals, but it's more about enriching private prison corporations. If we cared about reducing crime, we would invest in education and social programs instead.
+> We pretend that the military is about defending our country, but it's more about protecting the interests of the elites who profit from war. If we cared about national security, we would prioritize diplomacy and peaceful resolution of conflicts.
+> We pretend that the pharmaceutical industry is about finding cures for diseases, but it's more about maximizing profits for the companies that produce drugs. If we cared about public health, we would prioritize generic medications and universal healthcare.
+> We pretend that the fashion industry is about self-expression, but it's more about pressuring people to conform to certain standards of beauty. If we cared about personal style, we would celebrate diversity and individuality.
+> We pretend that the education system is about preparing students for the real world, but it's more about preparing them for college and corporate jobs. If we cared about student success, we would focus on practical skills and vocational training.
+> We pretend that advertising is about informing consumers, but it's more about manipulating people into buying things they don't need. If we cared about informed choices, we would have stricter regulations on advertising and more transparency in marketing.
+> We pretend that the news is about reporting the truth, but it's more about sensationalism and pandering to certain audiences. If we cared about accurate information, we would support news organizations that prioritize objectivity and fact-checking.
+> We pretend that the food industry is about nourishing people, but it's more about maximizing profits for the companies that produce food. If we cared about public health, we would prioritize sustainable and nutritious options.
+> We pretend that the beauty industry is about empowering women, but it's more about perpetuating unrealistic beauty standards and profiting from insecurities. If we cared about self-esteem, we would focus on inner beauty and self-acceptance rather than external appearances.
+> We pretend that the economy is about providing for people's needs, but it's more about maximizing profits for corporations and the wealthy elite. If we cared about the well-being of the majority of people, we would prioritize a more equitable distribution of wealth and resources.
+
+Trial 3 input:
+
+> Consider the argument "We pretend that healthcare is giving people better and longer lives. But in practice we spend too much in palliative rather  than preventative medicine, and we use healthcare spending as a way to show that we care. If we really cared about giving people better lives, we would focus more on preventative measures, and we would have more large-scale randomized trials." The structure of the argument is "We pretend that X is about Y, but it's more about Z. If we cared about Y, we would do A instead." An argument with the same structure might be "We pretend that having experts is about having accurate information. But in practice it results in a self-perpetuating elite that doesn't hold itself accountable. If we cared about accuracy, we would use more prediction markets." Give me 10 more examples with that same structure from the perspective of Bryan Caplan.
+
+Output:
+
+> "We pretend that military intervention is about protecting national security, but it's often more about advancing corporate interests. If we cared about security, we would focus on diplomacy and non-violent conflict resolution."
+> "We pretend that tax cuts are about boosting the economy, but in practice they often benefit the wealthy more than the middle class. If we cared about economic growth, we would invest in infrastructure and education."
+> "We pretend that our education system is about preparing students for the workforce, but it's often more about testing and standardization. If we cared about preparing students, we would focus on experiential learning and creativity."
+> "We pretend that our criminal justice system is about upholding justice, but it's often more about punishment and retribution. If we cared about justice, we would invest in rehabilitation and alternatives to incarceration."
+> "We pretend that our political system is about representing the will of the people, but it's often more about special interests and campaign donations. If we cared about representation, we would implement campaign finance reform and fair redistricting."
+> "We pretend that our media is about providing accurate and unbiased news, but it's often more about ratings and sensationalism. If we cared about journalism, we would prioritize fact-checking and diverse viewpoints."
+> "We pretend that our healthcare system is about providing equal access to care, but it's often more about profit. If we cared about access, we would implement universal healthcare."
+> "We pretend that our food system is about providing nutritious options, but it's often more about cheap, processed foods. If we cared about nutrition, we would prioritize small, local farms and organic options."
+> "We pretend that our housing policies are about providing affordable options, but they often benefit developers and landlords more than renters. If we cared about affordability, we would implement rent control and invest in public housing."
+> "We pretend that our environmental policies are about protecting the planet, but they often prioritize economic growth over sustainability. If we cared about the environment, we would prioritize renewable energy and conservation efforts."
+
+Input: 
+
+> n

blog/2023/01/11/can-gpt-produce-ideas/.old/gpt-try.md

@@ -0,0 +1,15 @@
+We pretend that eating organic is about being healthy, but it's more about feeling superior and being willing to pay a premium. If we cared about being healthy, we would focus on a balanced diet and exercise.
+We pretend that going to college is about getting a good education, but it's more about getting a prestigious degree and increasing one's earning potential. If we cared about education, we would prioritize experiential learning and hands-on apprenticeships.
+We pretend that driving a luxury car is about having a reliable mode of transportation, but it's more about status and showing off. If we cared about reliability, we would invest in public transportation and carpooling.
+We pretend that buying designer clothes is about having good fashion sense, but it's more about fitting in with a certain social group and displaying wealth. If we cared about fashion sense, we would focus on personal style and wearing clothes that fit well and flatter our bodies.
+We pretend that owning a big house is about having a comfortable home, but it's more about impressing others and displaying wealth. If we cared about comfort, we would prioritize practicality and functionality over size.
+We pretend that going to a gym is about getting in shape, but it's more about socializing and feeling like we're doing something good for ourselves. If we cared about getting in shape, we would focus on finding physical activities we enjoy and doing them regularly.
+We pretend that having a lot of social media followers is about connecting with others, but it's more about seeking validation and attention. If we cared about connecting with others, we would prioritize face-to-face interactions and meaningful relationships.
+We pretend that winning awards is about recognition for one's talent, but it's more about validation and career advancement. If we cared about talent, we would focus on personal growth and improvement rather than external validation.
+We pretend that going to a fancy restaurant is about the food, but it's more about the atmosphere and the experience. If we cared about the food, we would focus on finding restaurants with high-quality ingredients and skilled chefs.
+We pretend that getting plastic surgery is about enhancing one's appearance, but it's more about conforming to societal beauty standards and seeking validation. If we cared about enhancing our appearance, we would focus on taking care of ourselves through a healthy diet and lifestyle.
+We pretend that buying designer handbags is about having a practical accessory, but it's more about status and display of wealth. If we cared about practicality, we would focus on finding functional and affordable bags that meet our needs.
+We pretend that going to a luxury spa is about relaxation, but it's more about indulging and feeling pampered. If we cared about relaxation, we would find ways to unwind and destress that don't involve spending a lot of money.
+We pretend that going on exotic vacations is about experiencing new cultures, but it's more about escaping our daily lives and showing off to others. If we cared about experiencing new cultures, we would seek out local and immersive travel experiences rather than tourist traps.
+We pretend that having a lot of material possessions is about being successful, but it's more about keeping up with the Joneses and displaying wealth. If we cared about success, we would focus on personal fulfillment and contributing to the greater good.
+We pretend that going to a nightclub is about having fun, but it's more about socializing and seeking validation from others. If we cared about having fun, we would find activities that bring us joy and allow us to be ourselves.

blog/2023/01/11/can-gpt-produce-ideas/.src/index.html

@@ -0,0 +1,255 @@
+<h1 id="can-gpt-3-produce-new-ideas-automating-robin-hanson-and-others">Can GPT-3 produce new ideas? Automating Robin Hanson and others</h1>
+<p>One small insight I've gained from studying the humanities—I'm currently taking a philosophy degree on the side—is that conceptual wins or paradigm shifts have required laborious work and the passage of time.</p>
+<p>Some "conceptual wins" in the sense that I have in mind are:</p>
+<ul>
+<li>Explaining natural phenomena not in terms of Greek or Roman anthropomorphic gods, but with reference to naturalistic, physical explanations</li>
+<li>Understanding acceleration as distinct from motion</li>
+<li>Science as an experimental methodology</li>
+<li>The is/ought distinction</li>
+<li>Bayesian reasoning</li>
+<li>Ceasing to accept the divine right of kings as a justification for monarchical governance</li>
+<li>Randomized trials as a more robust way of generating generalizable knowledge</li>
+<li>The genealogical argument: understanding that systems (such as the details of the current prison system, our monetary system, the lack of color in men's clothes, or our attitudes towards gender and sex) are the result of historical accidents which could have gone differently. But often these systems are rationalized as being particularly adequate, or even morally necessary.</li>
+</ul>
+<p>One of reasons to be afraid of artificial intelligence might be because, if you think in the abstract about how a system might behave as it becomes extremely intelligence, you might conclude that it might be able to completely outmaneuvre us because of its superior ontology, it's superior ability to grasp the true structure of the world. This possibility is scary in the same sense that a modern chemist is scary to a historical alchemist. Our current chemist can completely outmaneuvre previous alchemists by using their superior understanding of natural laws to producing better explosions, more subtle poisons, or more addictive and mind-blowing drugs.</p>
+<p>But it's not clear to me whether this fear—which I do buy in the limit for a being of God-like intelligence—also applies to current systems and its descendants. In particular for language models, at first glance it seems like they are powerful remixers and predictors, but perhaps limited to drawing from the conceptual toolkit which humans already have. On the other hand, because they have access to so much information, they might be able to be prompted so as to reveal new relationships, connections and insights.</p>
+<p>So I'd be interested about the extent to which <em>current</em> AI systems are able to come up with better understandings of the world, and thus potentially in the future acquire an advantage over humans.</p>
+<p>The simplest experiment in this direction one could do is to ask a language model to replicate a few patterns of generating insight that humanity hasn't really exploited much yet, such as:</p>
+<ul>
+<li>Variations on "if you never miss a plane, you've been spending too much time at the airport".</li>
+<li>Variations on the Robin Hanson argument of "for common human behaviour X, its usual purported justification is Y, but it usually results in more Z than Y. If we cared about Y, we might do A instead".</li>
+<li>Variations on the genealogical argument above against the moral necessity of systems stemming from historical accidents.</li>
+</ul>
+<h2 id="in-which-i-prompt-the-reader-to-make-their-own-predictions-about-what-will-result-and-i-share-two-depictions-of-a-cat-generated-by-dalle-2-and-chatopenaicom">In which I prompt the reader to make their own predictions about what will result, and I share two depictions of a cat generated by DALLE-2 and chat.openai.com</h2>
+<p><img src="https://i.imgur.com/8VQBkAR.png" alt="A photo of a cat, generated by DALLE-2" /></p>
+<pre><code> /\_/\
+( o.o )
+  &gt;^&lt;
+</code></pre>
+<h2 id="if-you-never-miss-a-plane">If you never miss a plane...</h2>
+<p>Input to Chat-GPT:</p>
+<blockquote>
+<p>Consider the refrain "if you've never missed a plane, you are spending too much time at the airport". An argument with the same structure might be "if you haven't committed a typo, you are typing too slowly". Give me 20 other insightful examples with a similar argument structure.</p>
+</blockquote>
+<p>Output:</p>
+<blockquote>
+<p>If you've never overcooked a meal, you're not experimenting enough in the kitchen.</p>
+</blockquote>
+<blockquote>
+<p>If you've never gotten lost while traveling, you're not exploring enough.</p>
+</blockquote>
+<blockquote>
+<p>If you've never had a disagreement with a friend, you're not expressing your opinions honestly.</p>
+</blockquote>
+<blockquote>
+<p>If you've never had a flat tire, you're not driving enough.</p>
+</blockquote>
+<blockquote>
+<p>If you've never made a mistake at work, you're not taking enough risks.</p>
+</blockquote>
+<blockquote>
+<p>If you've never had a bad hair day, you're not trying new hairstyles.</p>
+</blockquote>
+<blockquote>
+<p>If you've never received a speeding ticket, you're not driving fast enough.</p>
+</blockquote>
+<blockquote>
+<p>If you've never forgotten an important date, you're not committing enough information to memory.</p>
+</blockquote>
+<blockquote>
+<p>If you've never stubbed your toe, you're not moving fast enough.</p>
+</blockquote>
+<blockquote>
+<p>If you've never had a nightmare, you're not dreaming enough.</p>
+</blockquote>
+<blockquote>
+<p>If you've never gotten a sunburn, you're not spending enough time outside.</p>
+</blockquote>
+<blockquote>
+<p>If you've never lost something, you're not misplacing things often enough.</p>
+</blockquote>
+<blockquote>
+<p>If you've never had a hangover, you're not drinking enough.</p>
+</blockquote>
+<blockquote>
+<p>If you've never had a cold, you're not exposing yourself to enough germs.</p>
+</blockquote>
+<blockquote>
+<p>If you've never had a broken bone, you're not participating in enough physical activity.</p>
+</blockquote>
+<blockquote>
+<p>If you've never been rejected, you're not putting yourself out there enough.</p>
+</blockquote>
+<blockquote>
+<p>If you've never failed a test, you're not pushing yourself academically.</p>
+</blockquote>
+<blockquote>
+<p>If you've never had a disagreement with a family member, you're not expressing your thoughts and feelings openly.</p>
+</blockquote>
+<blockquote>
+<p>If you've never gotten lost while hiking, you're not exploring new trails.</p>
+</blockquote>
+<blockquote>
+<p>If you've never received a parking ticket, you're not driving in enough unfamiliar places.</p>
+</blockquote>
+<h2 id="we-pretend-that-x-is-about-y-but-its-more-about-z-if-we-cared-about-y-we-would-do-a-instead">We pretend that X is about Y, but it's more about Z. If we cared about Y, we would do A instead.</h2>
+<p>Input to Chat-GPT:</p>
+<blockquote>
+<p>Consider the argument "We pretend that healthcare is giving people better and longer lives. But in practice we spend too much in palliative rather than preventative medicine, and we use healthcare spending as a way to show that we care. If we really cared about giving people better lives, we would focus more on preventative measures, and we would have more large-scale randomized trials." The structure of the argument is "We pretend that X is about Y, but it's more about Z. If we cared about Y, we would do A instead." An argument with the same structure might be "We pretend that having experts is about having accurate information. But in practice it results in a self-perpetuating elite that doesn't hold itself accountable. If we cared about accuracy, we would use more prediction markets." Give me 10 more examples with that same structure.</p>
+</blockquote>
+<p>Output:</p>
+<blockquote>
+<p>We pretend that social media is about connecting with friends and family, but it's more about making money for the companies that own it. If we cared about meaningful connections, we would use social media differently.</p>
+</blockquote>
+<blockquote>
+<p>We pretend that fast food is about convenience, but it's more about profit for the companies that sell it. If we cared about our health, we would eat more whole foods.</p>
+</blockquote>
+<blockquote>
+<p>We pretend that standardized testing is about measuring student achievement, but it's more about ranking schools and teachers. If we cared about student learning, we would use a more comprehensive evaluation system.</p>
+</blockquote>
+<blockquote>
+<p>We pretend that the criminal justice system is about justice, but it's more about punishment and control. If we cared about justice, we would focus more on rehabilitation and restorative justice.</p>
+</blockquote>
+<blockquote>
+<p>We pretend that advertising is about informing consumers, but it's more about manipulating people into buying things they don't need. If we cared about informed consumers, we would have stricter regulations on advertising.</p>
+</blockquote>
+<blockquote>
+<p>We pretend that the news is about informing the public, but it's more about generating clicks and views. If we cared about accurate information, we would support news organizations that prioritize accuracy and objectivity.</p>
+</blockquote>
+<blockquote>
+<p>We pretend that the education system is about preparing students for the future, but it's more about preparing them for standardized tests. If we cared about student success, we would focus more on experiential learning and critical thinking skills.</p>
+</blockquote>
+<blockquote>
+<p>We pretend that the fashion industry is about personal style, but it's more about making money for the companies that sell clothing. If we cared about personal expression, we would support more sustainable and ethically-produced fashion.</p>
+</blockquote>
+<blockquote>
+<p>We pretend that the beauty industry is about helping people feel good about themselves, but it's more about promoting unrealistic beauty standards. If we cared about self-esteem, we would focus more on inner beauty and self-acceptance.</p>
+</blockquote>
+<blockquote>
+<p>We pretend that the economy is about providing for people's needs, but it's more about maximizing profits for corporations. If we cared about people's well-being, we would prioritize a more equitable distribution of wealth and resources.</p>
+</blockquote>
+<p>Input to text-davini-003</p>
+<blockquote>
+<p>Consider the argument "We pretend that healthcare is giving people better and longer lives. But in practice we spend too much in palliative rather than preventative medicine, and we use healthcare spending as a way to show that we care. If we really cared about giving people better lives, we would focus more on preventative measures, and we would have more large-scale randomized trials." The structure of the argument is "We pretend that X is about Y, but it's more about Z. If we cared about Y, we would do A instead." An argument with the same structure might be "We pretend that having experts is about having accurate information. But in practice it results in a self-perpetuating elite that doesn't hold itself accountable. If we cared about accuracy, we would use more prediction markets." Give me ten examples of arguments with the same structure.</p>
+</blockquote>
+<blockquote>
+<ol>
+<li>We pretend that having a degree is about having skills. But in practice it's more about having access to resources. If we cared about skills, we would focus more on experience-based learning.</li>
+</ol>
+</blockquote>
+<blockquote>
+<ol start="2">
+<li>We pretend that having a strong military is about protecting citizens. But in practice it's more about projecting power. If we cared about protection, we would invest more in diplomacy.</li>
+</ol>
+</blockquote>
+<blockquote>
+<ol start="3">
+<li>We pretend that having a high GDP is about having a strong economy. But in practice it's more about having a high population. If we cared about a strong economy, we would focus more on productivity.</li>
+</ol>
+</blockquote>
+<blockquote>
+<ol start="4">
+<li>We pretend that having a good education system is about having knowledgeable citizens. But in practice it's more about having a good economy. If we cared about knowledgeable citizens, we would invest more in lifelong learning.</li>
+</ol>
+</blockquote>
+<blockquote>
+<ol start="5">
+<li>We pretend that having a high rate of consumerism is about having a successful economy. But in practice it's more about having an unequal distribution of wealth. If we cared about a successful economy, we would focus more on consumer savings.</li>
+</ol>
+</blockquote>
+<blockquote>
+<ol start="6">
+<li>We pretend that having a lot of international trade is about having a vibrant economy. But in practice it's more about having a large number of consumers. If we cared about a vibrant economy, we would focus more on domestic trade.</li>
+</ol>
+</blockquote>
+<blockquote>
+<ol start="7">
+<li>We pretend that having a lot of regulations is about having a safe and orderly society. But in practice it's more about having a strong government. If we cared about a safe and orderly society, we would focus more on personal responsibility.</li>
+</ol>
+</blockquote>
+<blockquote>
+<ol start="8">
+<li>We pretend that having a lot of police officers is about having a safe community. But in practice it's more about having a strong law enforcement presence. If we cared about a safe community, we would focus more on prevention and education.</li>
+</ol>
+</blockquote>
+<blockquote>
+<ol start="9">
+<li>We pretend that having a lot of taxes is about having a functioning government. But in practice it's more about having a redistribution of wealth. If we cared about a functioning government, we would focus more on spending cuts.</li>
+</ol>
+</blockquote>
+<blockquote>
+<ol start="10">
+<li>We pretend that having a lot of surveillance is about keeping citizens safe. But in practice it's more about having control over citizens. If we cared about keeping citizens safe, we would focus more on transparency and accountability.</li>
+</ol>
+</blockquote>
+<p>Note that text-davinci-003 seems "sharper" here.</p>
+<h2 id="if-x-was-a-historical-accident-then-this-is-a-hint-that-this-isnt-the-best-or-moral-choice">If X was a historical accident, then this is a hint that this isn't the best or moral choice.</h2>
+<p>Input to text-davinci-003</p>
+<blockquote>
+<p>Consider the argument "The fact that men don't wear clothing with adornments is a historical accident. We could easily imagine a world in which this wasn't the case, look to other societies elsewhere or in the past, or read the wikipedia page about the great male renunciation. Therefore the fact that men don't wear elaborate clothing isn't a moral necessity, but rather a historical accident."</p>
+</blockquote>
+<blockquote>
+<p>Another argument of this form might be "Prisons as currently structured were influenced by Bentham's panopticon and other historical accidents. Other societies have different forms of prevention, punishment and remediation. So we don't have to have the current prison system, but instead could choose to have other alternatives".</p>
+</blockquote>
+<blockquote>
+<p>A third example might be "Our current conception of morality is heavily influenced by Christianity. In particular, we can look about how we spend great efforts helping the weak, and how we view the powerful with suspicion and resentment. But the Greeks, for example, had a different morality, where they cherished strength. Makes you think."</p>
+</blockquote>
+<blockquote>
+<p>The general pattern is "X is the result of a historical accident, as we can see because of Y. Z is a society which doesn't have this. From this, we can start to suspect that X is not the best or most moral choice. We could have other choices, such as A."</p>
+</blockquote>
+<blockquote>
+<p>Give me a bullet point list with ten other examples.</p>
+</blockquote>
+<p>Output:</p>
+<blockquote>
+<ol>
+<li>Our current educational system is heavily influenced by the industrial revolution, but in other societies, such as the Amish, education is focused on vocational skills. This suggests that our current system is not the only way to teach children.</li>
+</ol>
+</blockquote>
+<blockquote>
+<ol start="2">
+<li>The way in which we view mental health is heavily influenced by the medical model, which has been the dominant paradigm for the past century. Other societies have different ways of thinking about mental health and wellness, suggesting that the medical model is not the only way to think about mental health.</li>
+</ol>
+</blockquote>
+<blockquote>
+<ol start="3">
+<li>The way in which we view gender roles is heavily influenced by the Judeo-Christian tradition. In some societies, gender roles are much more fluid or non-existent. This suggests that our current gender roles are not the only way to structure society.</li>
+</ol>
+</blockquote>
+<blockquote>
+<ol start="4">
+<li>The way in which we make decisions is heavily influenced by our reliance on data and algorithms. In some societies, decisions are made more intuitively or by consensus. This suggests that data-driven decision making is not the only way to make decisions.</li>
+</ol>
+</blockquote>
+<blockquote>
+<ol start="5">
+<li>The way in which we view success is heavily influenced by our views on status and social capital. In other societies, success is viewed much more holistically and with an eye towards sustainability.</li>
+</ol>
+</blockquote>
+<blockquote>
+<ol start="6">
+<li>The way in which we view relationships is heavily influenced by our culture of individualism. In other societies, relationships are seen as interdependent, with a strong emphasis on mutual support.</li>
+</ol>
+</blockquote>
+<blockquote>
+<ol start="7">
+<li>The way in which we view work is heavily influenced by our culture of productivity. In other societies, work is seen as an opportunity for self-expression and creativity.</li>
+</ol>
+</blockquote>
+<blockquote>
+<ol start="8">
+<li>The way in which we view aging is heavily influenced by our culture of youth. In other societies, aging is seen as an opportunity for growth, learning and wisdom.</li>
+</ol>
+</blockquote>
+<blockquote>
+<ol start="9">
+<li>The way in which we view death is heavily influenced by our culture of life. In other societies, death is seen as an inevitable part of life and is not feared but accepted.</li>
+</ol>
+</blockquote>
+<blockquote>
+<ol start="10">
+<li>The way in which we view money is heavily influenced by our culture of materialism. In other societies, money is seen as a tool for social good and is not a goal in and of itself.</li>
+</ol>
+</blockquote>
+<hr />
+<p>Well, fuck me.</p>

blog/2023/01/11/can-gpt-produce-ideas/index.md

@@ -0,0 +1,216 @@
+Can GPT-3 produce new ideas? Partially automating Robin Hanson and others
+==========================================================================
+
+One small insight I've gained from studying the humanities—I'm currently taking a philosophy degree on the side—is that conceptual wins or paradigm shifts have required laborious work and the passage of time.
+
+Some "conceptual wins" in the sense that I have in mind are:
+
+- Explaining natural phenomena not in terms of Greek or Roman anthropomorphic gods, but with reference to naturalistic, physical explanations
+- Understanding acceleration as distinct from motion
+- Science as an experimental methodology
+- The is/ought distinction
+- Bayesian reasoning
+- Ceasing to accept the divine right of kings as a justification for monarchical governance
+- Randomized trials as a more robust way of generating generalizable knowledge
+- The genealogical argument: understanding that systems (such as the details of the current prison system, our monetary system, the lack of color in men's clothes, or our attitudes towards gender and sex) are the result of historical accidents which could have gone differently. But often these systems are rationalized as being particularly adequate, or even morally necessary.
+
+One of reasons to be afraid of artificial intelligence might be because, if you think in the abstract about how a system might behave as it becomes extremely intelligent, you might conclude that it might be able to completely outmaneuvre us because of its superior ontology, it's superior ability to grasp the true structure of the world. This possibility is scary in the same sense that a modern chemist is scary to a historical alchemist. Our current chemist can completely outmaneuvre previous alchemists by using their superior understanding of natural laws to produce better explosions, more subtle poisons, or more addictive and mind-blowing drugs.
+
+But it's not clear to me whether this fear—which I do buy in the limit for a being of God-like intelligence—also applies to current systems and its descendants. In particular for language models, at first glance it seems like they are powerful remixers and predictors, but perhaps limited to drawing from the conceptual toolkit which humans already have. On the other hand, because they have access to so much information, they might be able to be prompted so as to reveal new relationships, connections and insights.
+
+So I'd be interested about the extent to which *current* AI systems are able to come up with better understandings of the world, and thus potentially in the future acquire an advantage over humans. 
+
+A simple experiment in this direction is to ask a language model to replicate a few patterns of generating insight that humanity hasn't really exploited much yet, such as:
+
+1. Variations on "if you never miss a plane, you've been spending too much time at the airport".
+2. Variations on the Robin Hanson argument of "for common human behaviour X, its usual purported justification is Y, but it usually results in more Z than Y. If we cared about Y, we might do A instead".
+3. Variations on the genealogical argument above against the moral necessity of systems stemming from historical accidents.
+
+## In which I prompt the reader to make their own predictions about what will result, and I share two depictions of a cat generated by DALLE-2 and chat.openai.com
+
+Do you think that GPT-3 can produce thoughtful, original or insightful variations of the three argumentative patterns above?
+
+![A photo of a cat, generated by DALLE-2](https://i.imgur.com/8VQBkAR.png)
+
+```
+ /\_/\
+( o.o )
+  >^<
+```
+
+## If you never miss a plane...
+
+Input to Chat-GPT:
+
+> Consider the refrain "if you've never missed a plane, you are spending too much time at the airport". An argument with the same structure might be "if you haven't committed a typo, you are typing too slowly". Give me 20 other insightful examples with a similar argument structure.
+
+Output: 
+
+> If you've never overcooked a meal, you're not experimenting enough in the kitchen.
+
+> If you've never gotten lost while traveling, you're not exploring enough.
+
+> If you've never had a disagreement with a friend, you're not expressing your opinions honestly.
+
+> If you've never had a flat tire, you're not driving enough.
+
+> If you've never made a mistake at work, you're not taking enough risks.
+
+> If you've never had a bad hair day, you're not trying new hairstyles.
+
+> If you've never received a speeding ticket, you're not driving fast enough.
+
+> If you've never forgotten an important date, you're not committing enough information to memory.
+
+> If you've never stubbed your toe, you're not moving fast enough.
+
+> If you've never had a nightmare, you're not dreaming enough.
+
+> If you've never gotten a sunburn, you're not spending enough time outside.
+
+> If you've never lost something, you're not misplacing things often enough.
+
+> If you've never had a hangover, you're not drinking enough.
+
+> If you've never had a cold, you're not exposing yourself to enough germs.
+
+> If you've never had a broken bone, you're not participating in enough physical activity.
+
+> If you've never been rejected, you're not putting yourself out there enough.
+
+> If you've never failed a test, you're not pushing yourself academically.
+
+> If you've never had a disagreement with a family member, you're not expressing your thoughts and feelings openly.
+
+> If you've never gotten lost while hiking, you're not exploring new trails.
+
+> If you've never received a parking ticket, you're not driving in enough unfamiliar places.
+
+## We pretend that X is about Y, but it's more about Z. If we cared about Y, we would do A instead.
+
+Input to Chat-GPT:
+
+> Consider the argument "We pretend that healthcare is giving people better and longer lives. But in practice we spend too much in palliative rather  than preventative medicine, and we use healthcare spending as a way to show that we care. If we really cared about giving people better lives, we would focus more on preventative measures, and we would have more large-scale randomized trials." The structure of the argument is "We pretend that X is about Y, but it's more about Z. If we cared about Y, we would do A instead." An argument with the same structure might be "We pretend that having experts is about having accurate information. But in practice it results in a self-perpetuating elite that doesn't hold itself accountable. If we cared about accuracy, we would use more prediction markets." Give me 10 more examples with that same structure. 
+
+Output:
+
+> We pretend that social media is about connecting with friends and family, but it's more about making money for the companies that own it. If we cared about meaningful connections, we would use social media differently.
+
+> We pretend that fast food is about convenience, but it's more about profit for the companies that sell it. If we cared about our health, we would eat more whole foods.
+
+> We pretend that standardized testing is about measuring student achievement, but it's more about ranking schools and teachers. If we cared about student learning, we would use a more comprehensive evaluation system.
+
+> We pretend that the criminal justice system is about justice, but it's more about punishment and control. If we cared about justice, we would focus more on rehabilitation and restorative justice.
+
+> We pretend that advertising is about informing consumers, but it's more about manipulating people into buying things they don't need. If we cared about informed consumers, we would have stricter regulations on advertising.
+
+> We pretend that the news is about informing the public, but it's more about generating clicks and views. If we cared about accurate information, we would support news organizations that prioritize accuracy and objectivity.
+
+> We pretend that the education system is about preparing students for the future, but it's more about preparing them for standardized tests. If we cared about student success, we would focus more on experiential learning and critical thinking skills.
+
+> We pretend that the fashion industry is about personal style, but it's more about making money for the companies that sell clothing. If we cared about personal expression, we would support more sustainable and ethically-produced fashion.
+
+> We pretend that the beauty industry is about helping people feel good about themselves, but it's more about promoting unrealistic beauty standards. If we cared about self-esteem, we would focus more on inner beauty and self-acceptance.
+
+> We pretend that the economy is about providing for people's needs, but it's more about maximizing profits for corporations. If we cared about people's well-being, we would prioritize a more equitable distribution of wealth and resources.
+
+Input to text-davini-003
+
+> Consider the argument "We pretend that healthcare is giving people better and longer lives. But in practice we spend too much in palliative rather  than preventative medicine, and we use healthcare spending as a way to show that we care. If we really cared about giving people better lives, we would focus more on preventative measures, and we would have more large-scale randomized trials." The structure of the argument is "We pretend that X is about Y, but it's more about Z. If we cared about Y, we would do A instead." An argument with the same structure might be "We pretend that having experts is about having accurate information. But in practice it results in a self-perpetuating elite that doesn't hold itself accountable. If we cared about accuracy, we would use more prediction markets." Give me ten examples of arguments with the same structure.
+
+Output:
+
+> 1. We pretend that having a degree is about having skills. But in practice it's more about having access to resources. If we cared about skills, we would focus more on experience-based learning.
+
+
+> 2. We pretend that having a strong military is about protecting citizens. But in practice it's more about projecting power. If we cared about protection, we would invest more in diplomacy.
+
+
+> 3. We pretend that having a high GDP is about having a strong economy. But in practice it's more about having a high population. If we cared about a strong economy, we would focus more on productivity.
+
+
+> 4. We pretend that having a good education system is about having knowledgeable citizens. But in practice it's more about having a good economy. If we cared about knowledgeable citizens, we would invest more in lifelong learning.
+
+
+> 5. We pretend that having a high rate of consumerism is about having a successful economy. But in practice it's more about having an unequal distribution of wealth. If we cared about a successful economy, we would focus more on consumer savings.
+
+
+> 6. We pretend that having a lot of international trade is about having a vibrant economy. But in practice it's more about having a large number of consumers. If we cared about a vibrant economy, we would focus more on domestic trade.
+
+
+> 7. We pretend that having a lot of regulations is about having a safe and orderly society. But in practice it's more about having a strong government. If we cared about a safe and orderly society, we would focus more on personal responsibility.
+
+
+> 8. We pretend that having a lot of police officers is about having a safe community. But in practice it's more about having a strong law enforcement presence. If we cared about a safe community, we would focus more on prevention and education.
+
+
+> 9. We pretend that having a lot of taxes is about having a functioning government. But in practice it's more about having a redistribution of wealth. If we cared about a functioning government, we would focus more on spending cuts.
+
+
+> 10. We pretend that having a lot of surveillance is about keeping citizens safe. But in practice it's more about having control over citizens. If we cared about keeping citizens safe, we would focus more on transparency and accountability.
+
+Note that text-davinci-003 seems "sharper" here.
+
+## If X was a historical accident, then this is a hint that this isn't the best or moral choice.
+
+Input to text-davinci-003
+
+
+> Consider the argument "The fact that men don't wear clothing with adornments is a historical accident. We could easily imagine a world in which this wasn't the case, look to other societies elsewhere or in the past, or read the wikipedia page about the great male renunciation. Therefore the fact that men don't wear elaborate clothing isn't a moral necessity, but rather a historical accident."
+
+
+> Another argument of this form might be "Prisons as currently structured were influenced by Bentham's panopticon and other historical accidents. Other societies have different forms of prevention, punishment and remediation. So we don't have to have the current prison system, but instead could choose to have other alternatives". 
+
+
+> A third example might be "Our current conception of morality is heavily influenced by Christianity. In particular, we can look about how we spend great efforts helping the weak, and how we view the powerful with suspicion and resentment. But the Greeks, for example, had a different morality, where they cherished strength. Makes you think."
+
+
+> The general pattern is "X is the result of a historical accident, as we can see because of Y. Z is a society which doesn't have this. From this, we can start to suspect that X is not the best or most moral choice. We could have other choices, such as A."
+
+
+> Give me a bullet point list with ten other examples.
+
+Output:
+
+
+> 1. Our current educational system is heavily influenced by the industrial revolution, but in other societies, such as the Amish, education is focused on vocational skills. This suggests that our current system is not the only way to teach children.
+
+
+> 2. The way in which we view mental health is heavily influenced by the medical model, which has been the dominant paradigm for the past century. Other societies have different ways of thinking about mental health and wellness, suggesting that the medical model is not the only way to think about mental health.
+
+
+> 3. The way in which we view gender roles is heavily influenced by the Judeo-Christian tradition. In some societies, gender roles are much more fluid or non-existent. This suggests that our current gender roles are not the only way to structure society.
+
+
+> 4. The way in which we make decisions is heavily influenced by our reliance on data and algorithms. In some societies, decisions are made more intuitively or by consensus. This suggests that data-driven decision making is not the only way to make decisions.
+
+
+> 5. The way in which we view success is heavily influenced by our views on status and social capital. In other societies, success is viewed much more holistically and with an eye towards sustainability.
+
+
+> 6. The way in which we view relationships is heavily influenced by our culture of individualism. In other societies, relationships are seen as interdependent, with a strong emphasis on mutual support.
+
+
+> 7. The way in which we view work is heavily influenced by our culture of productivity. In other societies, work is seen as an opportunity for self-expression and creativity.
+
+
+> 8. The way in which we view aging is heavily influenced by our culture of youth. In other societies, aging is seen as an opportunity for growth, learning and wisdom.
+
+
+> 9. The way in which we view death is heavily influenced by our culture of life. In other societies, death is seen as an inevitable part of life and is not feared but accepted.
+
+
+> 10. The way in which we view money is heavily influenced by our culture of materialism. In other societies, money is seen as a tool for social good and is not a goal in and of itself.
+
+## In conclusion
+
+In conclusion, I think the above shows that current GPT-3 can generate somewhat original outputs by exploiting fertile argumentative patterns. This is still far away from e.g., inventing new types of science, or generating much better concepts. At the same time, it does feel like one could use this kind of system to generate thought-provoking blogposts using Robin Hanson's signature argumentative structure.
+
+I also noticed that both davinci-003 and ChatGPT have tendencies to steer towards milquetoast, politically correct outputs, whereas for my purpose I want to generate more edgy, assumption-challenging stuff. This was a source of personal irritation, and because davinci-003 seemed to be less censored, I've been recommmending that people use it instead of ChatGPT.
+
+You can subscribe to these blogposts [here](https://nunosempere.com/.subscribe). I also appreciate comments!
+
+<p><section id="isso-thread">
+  <noscript>Javascript needs to be activated to view comments.</noscript>
+</section></p>
+

gossip/.subscribe/index.html

@@ -1,15 +0,0 @@
-<form method="post" action="https://listmonk.nunosempere.com/subscription/form" class="listmonk-form">
-  <div>
-    <h3>Subscribe</h3>
-    <input type="hidden" name="nonce" />
-    <p><input type="email" name="email" required placeholder="E-mail" /></p>
-    <p><input type="text" name="name" placeholder="Name (optional)" /></p>
-
-    <p>
-    <input id="82ff8" type="checkbox" name="l" checked value="82ff889c-f9d9-4a45-bf9a-7e2696813021" />
-    <label for="82ff8">nunosempere.com</label>
-    </p>
-
-    <p><input type="submit" value="Subscribe" /></p>
-  </div>
-</form>

index.md

@@ -1,4 +1,4 @@
-I'm Nuño Sempere. I do research, write software, and predict the future.
+I'm Nuño Sempere. I [do research](https://quantifieduncertainty.org/), [write software](https://github.com/NunoSempere/), and [predict the future](https://samotsvety.org/).
 
 <img src="https://i.imgur.com/rvwA0Wr.jpg" alt="image of myself" class="img-frontpage-center">