LESSWRONG
LW

NunoSempere
2656Ω11552734
Message
Dialogue
Subscribe

I am an independent research and programmer working at my own consultancy, Shapley Maximizers ÖU. I like to spend my time acquiring deeper models of the world, and generally becoming more formidable.  I'm also a fairly good forecaster: I started out on predicting on Good Judgment Open and CSET-Foretell, but now do most of my forecasting through Samotsvety, of which Scott Alexander writes:

Enter Samotsvety Forecasts. This is a team of some of the best superforecasters in the world. They won the CSET-Foretell forecasting competition by an absolutely obscene margin, “around twice as good as the next-best team in terms of the relative Brier score”. If the point of forecasting tournaments is to figure out who you can trust, the science has spoken, and the answer is “these guys”.


I used to post prolifically on the EA Forum, but nowadays, I post my research and thoughts at nunosempere.com / nunosempere.com/blog rather than on this forum, because:

  • I disagree with the EA Forum's moderation policy—they've banned a few disagreeable people whom I like, and I think they're generally a bit too censorious for my liking. 
  • The Forum website has become more annoying to me over time: more cluttered and more pushy in terms of curated and pinned posts (I've partially mitigated this by writing my own minimalistic frontend)
  • The above two issues have made me take notice that the EA Forum is beyond my control, and it feels like a dumb move to host my research in a platform that has goals different from my own. 

But a good fraction of my past research is still available here on the EA Forum. I'm particularly fond of my series on Estimating Value. And I haven't left the forum entirely: I remain subscribed to its RSS, and generally tend to at least skim all interesting posts.


I used to do research around longtermism, forecasting and quantification, as well as some programming, at the Quantified Uncertainty Research Institute (QURI). At QURI, I programmed Metaforecast.org, a search tool which aggregates predictions from many different platforms, which I still maintain. I spent some time in the Bahamas as part of the FTX EA Fellowship. Previously, I was a Future of Humanity Institute 2020 Summer Research Fellow, and then worked on a grant from the Long Term Future Fund to do "independent research on forecasting and optimal paths to improve the long-term." I used to write a Forecasting Newsletter which gathered a few thousand subscribers, but I stopped as the value of my time rose. I also generally enjoy winning bets against people too confident in their beliefs.

Before that, I studied Maths and Philosophy, dropped out in exasperation at the inefficiency, picked up some development economics; helped implement the European Summer Program on Rationality during 2017, 2018 2019, 2020 and 2022; worked as a contractor for various forecasting and programming projects; volunteered for various Effective Altruism organizations, and carried out many independent research projects. In a past life, I also wrote a popular Spanish literature blog, and remain keenly interested in Spanish poetry.


You can share feedback anonymously with me here.

Sequences

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
4NunoSempere's Shortform
5y
4
Forecasting Newsletter
Inner and Outer Alignment Failures in current forecasting systems
Prover-Estimator Debate: A New Scalable Oversight Protocol
NunoSempere1mo43

This is really cool!

Reply
Global Risks Weekly Roundup #19/2025: India/Pakistan ceasefire, US/China tariffs deal & OpenAI nonprofit control
NunoSempere2mo20

Particularly interested in LW's speculation about distributed computing, and whether you could see the largest training run via that method over the next few years.

Reply
Interest In Conflict Is Instrumentally Convergent
NunoSempere2mo30

Thanks, yes.

  1. The original post introduced a difference between the professionals/the curious/the oddballs/normal people/bad actors.
  2. People who have opinions about how [whatever] should be done are not normies (where [whatever] relates to defenses against bad actors)
  3. Normies are innocent but also the large majority of people.
  4. When learning that someone has opinions about [whatever], the prior probability of being a bad actor switches from #bad actor/(#professionals +#the curious +#the oddballs + #normal people + #bad actors) to #bad actor/(#professionals +#the curious +#the oddballs + #bad actors)
  5. That is, you are discarding this probability: #normal people/(#professionals +#the curious +#the oddballs + #normal people + #bad actors)
  6. Thus, the prior probability of someone interested in [whatever] being a bad actor rises.

I'm not saying anything the post isn't saying, I'm just pointing out that the forecasting/simple Bayesian tradition of knowledge really agrees with this post. You then have further arguments around the virtue of orienting the world around happy paths and normies, but still.

Reply
Interest In Conflict Is Instrumentally Convergent
NunoSempere2mo142

Makes me empathize with the defender :), but let me tell you, being interrogated in an airport for six hours trying to convince a US immigration agent that I'm an oddball not a danger is not fun

Reply
Interest In Conflict Is Instrumentally Convergent
NunoSempere2mo20

people who have opinions about how [whatever] should be done are unusually likely to be bad actors who want me to do [whatever] in such a way as to benefit them

But the inference is correct, no, since you are discarding the probability mass on "innocent normie", no?

Reply
Proposal: Liquid Prediction Markets for AI Forecasting
NunoSempere2mo30

Very interesting! will mention in my forecasting newsletter

Reply
Understanding Shapley Values with Venn Diagrams
NunoSempere2mo20

No, the shapley value hasn't been changed. The correct way to do this would have been, that, if:

A: $0
B: $0
A+B: $300

then

A: $0
B: $0

A+B: $0 (Carol vetoes) A+B: $300
A+C: $0
B+C: $0
A+B+C: $300

 

Your example is wrong becuase you are not leaving the A+B case unchanged.

 

I agree that "being more people" is a problem in coalitional dynamics with vetos, but I don't think this is a problem with the Shapley value solution. I agree that when trying to apply the Shapley value solution, you should make sure to set C's value as zero (even though it might hurt egos), etc.

Reply
The US Executive vs Supreme Court Deportations Clash
NunoSempere3mo-3-5

I think your contributions are sufficiently counterproductive (lengthy, wrong, uninformed) that per my "Reign of Terror" moderation policy I'm banning you from my posts. I met a person with your same name at a NY meetup a few years ago, and I don't have anything against you as a person & wish you the best. Maybe I'm unduly annoyed because I see some of my worst qualities in this comment (maybe something like futile disagreeableness). FWIW I would have been more sympathetic with your stance a few months ago, but I think that we since have much more data. If you feel strongly about this and we have a mutual acquaintance that can intercede & vouch for you I'll reconsider this.

Reply
The US Executive vs Supreme Court Deportations Clash
NunoSempere3mo20

The US also has a strong presidential system

No, the US has a system where power is divided across the three branches. Further, the President can release prisoners from federal prisons through a pardon.

Reply
The US Executive vs Supreme Court Deportations Clash
NunoSempere3mo31

Neither do you

I don't know with absolute certainty but I am really sure. I can observe that El Salvador has a strong presidential system, and Bukele a strong grip on power.

Neither do any of American judges issuing orders in this case

This is an interesting point about to what extent judges can make geopolitical judgment calls. The way they are handling this is by judging the administration on the steps it has taken. This could just be a strongly worded letter. So far that hasn't happened.

Reply
Load More
22US credit rating downgraded, $1T in Gulf state investments in the US, Kurdistan Workers’ Party disbanded | Sentinel Global Risks Weekly Roundup #20/2025
2mo
0
10Global Risks Weekly Roundup #19/2025: India/Pakistan ceasefire, US/China tariffs deal & OpenAI nonprofit control
2mo
1
31Global Risks Weekly Roundup #18/2025: US tariff shortages, military policing, Gaza famine.
2mo
2
44The US Executive vs Supreme Court Deportations Clash
3mo
12
42Sentinel's Global Risks Weekly Roundup #15/2025: Tariff yoyo, OpenAI slashing safety testing, Iran nuclear programme negotiations, 1K H5N1 confirmed herd infections.
3mo
0
13Sentinel's Global Risks Weekly Roundup #12/2025: Famine in Gaza, H7N9 outbreak, US geopolitical leadership weakening.
4mo
0
59Sentinel's Global Risks Weekly Roundup #11/2025. Trump invokes Alien Enemies Act, Chinese invasion barges deployed in exercise.
4mo
3
25Sentinel minutes #10/2025: Trump tariffs, US/China tensions, Claude code reward hacking.
4mo
0
8Forecasting newsletter #3/2025: Long march through the institutions
4mo
0
13Forecasting newsletter #2/2025: Forecasting meetup network
5mo
0
Load More
Ontological Crisis
3y
(+60/-52)
2017-2019 AI Alignment Prize
3y
(+136/-30)
2017-2019 AI Alignment Prize
3y
(+713)
2017-2019 AI Alignment Prize
3y
(+110)