Mo Putera

I've been lurking on LW since 2013, but only started posting recently. My day job was "analytics broadly construed" although I'm currently exploring applied prio-like roles; my degree is in physics; I used to write on Quora and Substack but stopped, although I'm still on the EA Forum. I'm based in Kuala Lumpur, Malaysia.

Wiki Contributions


That's not the sense I get from skimming his second most recent post, but I don't understand what he's getting at well enough to speak in his place.

Not an answer to your question, just an extended quote from the late Fields medalist Bill Thurston from his classic essay On proof and progress which seemed relevant:

Mathematicians have developed habits of communication that are often dysfunctional. Organizers of colloquium talks everywhere exhort speakers to explain things in elementary terms. Nonetheless, most of the audience at an average colloquium talk gets little of value from it. Perhaps they are lost within the first 5 minutes, yet sit silently through the remaining 55 minutes. Or perhaps they quickly lose interest because the speaker plunges into technical details without presenting any reason to investigate them. At the end of the talk, the few mathematicians who are close to the field of the speaker ask a question or two to avoid embarrassment.

... Outsiders are amazed at this phenomenon, but within the mathematical community, we dismiss it with shrugs. ...

Mathematical knowledge can be transmitted amazingly fast within a subfield. When a significant theorem is proved, it often (but not always) happens that the solution can be communicated in a matter of minutes from one person to another within the subfield. The same proof would be communicated and generally understood in an hour talk to members of the subfield. It would be the subject of a 15- or 20-page paper, which could be read and understood in a few hours or perhaps days by members of the subfield.

Why is there such a big expansion from the informal discussion to the talk to the paper? One-on-one, people use wide channels of communication that go far beyond formal mathematical language. They use gestures, they draw pictures and diagrams, they make sound effects and use body language. Communication is more likely to be two-way, so that people can concentrate on what needs the most attention. With these channels of communication, they are in a much better position to convey what’s going on, not just in their logical and linguistic facilities, but in their other mental facilities as well.

In talks, people are more inhibited and more formal. Mathematical audiences are often not very good at asking the questions that are on most people’s minds, and speakers often have an unrealistic preset outline that inhibits them from addressing questions even when they are asked. In papers, people are still more formal. Writers translate their ideas into symbols and logic, and readers try to translate back.

Why is there such a discrepancy between communication within a subfield and communication outside of subfields, not to mention communication outside mathematics?

Mathematics in some sense has a common language: a language of symbols, technical definitions, computations, and logic. This language efficiently conveys some, but not all, modes of mathematical thinking. Mathematicians learn to translate certain things almost unconsciously from one mental mode to the other, so that some statements quickly become clear. Different mathematicians study papers in different ways, but when I read a mathematical paper in a field in which I’m conversant, I concentrate on the thoughts that are between the lines. I might look over several paragraphs or strings of equations and think to myself “Oh yeah, they’re putting in enough rigamarole to carry such-and-such idea.” When the idea is clear, the formal setup is usually unnecessary and redundant—I often feel that I could write it out myself more easily than figuring out what the authors actually wrote. It’s like a new toaster that comes with a 16-page manual. If you already understand toasters and if the toaster looks like previous toasters you’ve encountered, you might just plug it in and see if it works, rather than first reading all the details in the manual.

People familiar with ways of doing things in a subfield recognize various patterns of statements or formulas as idioms or circumlocution for certain concepts or mental images. But to people not already familiar with what’s going on the same patterns are not very illuminating; they are often even misleading. The language is not alive except to those who use it. 

Okay, I liked that passage but maybe it wasn't very useful. Ravi Vakil's advice to potential PhD students attending talks seems more useful, especially the last bullet:

  • At the end of the talk, you should try to answer the questions: What question(s) is the speaker trying to answer? Why should we care about them? What flavor of results has the speaker proved? Do I have a small example of the phenonenon under discussion? You can even scribble down these questions at the start of the talk, and jot down answers to them during the talk.
  • Try to extract three words from the talk (no matter how tangentially related to the subject at hand) that you want to know the definition of. Then after the talk, ask me what they mean. ...
  • New version of the previous jot: try the "three things" exercise.
  • See if you can get one lesson from the talk (broadly interpreted). 
  • Try to ask one question at as many seminars as possible, either during the talk, or privately afterwards. The act of trying to formulating an interesting question (for you, not the speaker!) is a worthwhile exercise, and can focus the mind.

I'm guessing Rob is referring to footnote 54 in What do XPT forecasts tell us about AI risk?:

And while capabilities have been increasing very rapidly, research into AI safety, does not seem to be keeping pace, even if it has perhaps sped-up in the last two years. An isolated, but illustrative, data point of this can be seen in the results of the 2022 section of a Hypermind forecasting tournament: on most benchmarks, forecasters underpredicted progress, but they overpredicted progress on the single benchmark somewhat related to AI safety.

That last link is to Jacob Steinhardt's tweet linking to his 2022 post AI Forecasting: One Year In, on the results of their 2021 forecasting contest. Quote:

Progress on a robustness benchmark was slower than expected, and was the only benchmark to fall short of forecaster predictions. This is somewhat worrying, as it suggests that machine learning capabilities are progressing quickly, while safety properties are progressing slowly. ...

As a reminder, the four benchmarks were:

  • MATH, a mathematics problem-solving dataset;
  • MMLU, a test of specialized subject knowledge using high school, college, and professional multiple choice exams;
  • Something Something v2, a video recognition dataset; and
  • CIFAR-10 robust accuracy, a measure of adversarially robust vision performance.


Here are the actual results, as of today:

  • MATH: 50.3% (vs. 12.7% predicted)
  • MMLU: 67.5% (vs. 57.1% predicted)
  • Adversarial CIFAR-10: 66.6% (vs. 70.4% predicted)
  • Something Something v2: 75.3% (vs. 73.0% predicted)

That's all I got, no other predictions.

Great post, especially the companion piece :)

I'm tangentially reminded of professional modeler & health economist froolow's refactoring of GiveWell's cost-effectiveness models in his A critical review of GiveWell's 2022 cost-effectiveness model (sections 3 and 4), which I think of as complementary to your post in that it teaches-via-case-study how to level up your spreadsheet modeling. 

Here's GiveWell's model architecture:

And here's froolow's refactoring: 

The difference in micro-level architecture is also quite large:

As someone who's spent a lot of his (short) career building dashboards and models in Google Sheets, and having seen GiveWell's CEAs, I empathized with froolow's remarks here:

After the issue of uncertainty analysis, I’d say the model architecture is the second biggest issue I have with the GiveWell model, and really the closest thing to a genuine ‘error’ rather than a conceptual step which could be improved. Model architecture is how different elements of your model interact with each other, and how they are laid out to a user. 

It is fairly clear that the GiveWell team are not professional modellers, in the same way it would be obvious to a professional programmer that I am not a coder (this will be obvious as soon as you check the code in my Refactored model!). That is to say, there’s a lot of wasted effort in the GiveWell model which is typical when intelligent people are concentrating on making something functional rather than using slick technique. A very common manifestation of the ‘intelligent people thinking very hard about things’ school of model design is extremely cramped and confusing model architecture. This is because you have to be a straight up genius to try and design a model as complex as the GiveWell model without using modern model planning methods, and people at that level of genius don’t need crutches the rest of us rely on like clear and straightforward model layout. However, bad architecture is technical debt that you are eventually going to have to service on your model; when you hand it over to a new member of staff it takes longer to get that member of staff up to speed and increases the probability of someone making an error when they update the model.

I think you're right that I missed their point, thanks for pointing it out.

I have had experiences similar to Johannes' anecdote re: ignoring broken glass to not lose fragile threads of thought; they usually entailed extended deep work periods past healthy thresholds for unclear marginal gain, so the quotes above felt personally relevant as guardrails. But also my experiences don't necessarily generalize (as your hypothetical shows).

I'd be curious to know your model, and how it compares to some of John Wentworth's posts on the same IIRC.

These thoughts remind me of something Scott Alexander once wrote - that sometimes he hears someone say true but low status things - and his automatic thoughts are about how the person must be stupid to say something like that, and he has to consciously remind himself that what was said is actually true.

For anyone who's curious, this is what Scott said, in reference to him getting older – I remember it because I noticed the same in myself as I aged too:

I look back on myself now vs. ten years ago and notice I’ve become more cynical, more mellow, and more prone to believing things are complicated. For example: [list of insights] ...

All these seem like convincing insights. But most of them are in the direction of elite opinion. There’s an innocent explanation for this: intellectual elites are pretty wise, so as I grow wiser I converge to their position. But the non-innocent explanation is that I’m not getting wiser, I’m just getting better socialized. ...

I’m pretty embarassed by Parable On Obsolete Ideologies, which I wrote eight years ago. It’s not just that it’s badly written, or that it uses an ill-advised Nazi analogy. It’s that it’s an impassioned plea to jettison everything about religion immediately, because institutions don’t matter and only raw truth-seeking is important. If I imagine myself entering that debate today, I’d be more likely to take the opposite side. But when I read Parable, there’s…nothing really wrong with it. It’s a good argument for what it argues for. I don’t have much to say against it. Ask me what changed my mind, and I’ll shrug, tell you that I guess my priorities shifted. But I can’t help noticing that eight years ago, New Atheism was really popular, and now it’s really unpopular. Or that eight years ago I was in a place where having Richard Dawkins style hyperrationalism was a useful brand, and now I’m (for some reason) in a place where having James C. Scott style intellectual conservativism is a useful brand. A lot of the “wisdom” I’ve “gained” with age is the kind of wisdom that helps me channel James C. Scott instead of Richard Dawkins; how sure am I that this is the right path?

Sometimes I can almost feel this happening. First I believe something is true, and say so. Then I realize it’s considered low-status and cringeworthy. Then I make a principled decision to avoid saying it – or say it only in a very careful way – in order to protect my reputation and ability to participate in society. Then when other people say it, I start looking down on them for being bad at public relations. Then I start looking down on them just for being low-status or cringeworthy. Finally the idea of “low-status” and “bad and wrong” have merged so fully in my mind that the idea seems terrible and ridiculous to me, and I only remember it’s true if I force myself to explicitly consider the question. And even then, it’s in a condescending way, where I feel like the people who say it’s true deserve low status for not being smart enough to remember not to say it. This is endemic, and I try to quash it when I notice it, but I don’t know how many times it’s slipped my notice all the way to the point where I can no longer remember the truth of the original statement.

This was back in 2017. 

Holden advised against this:

Jog, don’t sprint. Skeptics of the “most important century” hypothesis will sometimes say things like “If you really believe this, why are you working normal amounts of hours instead of extreme amounts? Why do you have hobbies (or children, etc.) at all?” And I’ve seen a number of people with an attitude like: “THIS IS THE MOST IMPORTANT TIME IN HISTORY. I NEED TO WORK 24/7 AND FORGET ABOUT EVERYTHING ELSE. NO VACATIONS."

I think that’s a very bad idea.

Trying to reduce risks from advanced AI is, as of today, a frustrating and disorienting thing to be doing. It’s very hard to tell whether you’re being helpful (and as I’ve mentioned, many will inevitably think you’re being harmful).

I think the difference between “not mattering,” “doing some good” and “doing enormous good” comes down to how you choose the job, how good at it you are, and how good your judgment is (including what risks you’re most focused on and how you model them). Going “all in” on a particular objective seems bad on these fronts: it poses risks to open-mindedness, to mental health and to good decision-making (I am speaking from observations here, not just theory).

That is, I think it’s a bad idea to try to be 100% emotionally bought into the full stakes of the most important century - I think the stakes are just too high for that to make sense for any human being.

Instead, I think the best way to handle “the fate of humanity is at stake” is probably to find a nice job and work about as hard as you’d work at another job, rather than trying to make heroic efforts to work extra hard. (I criticized heroic efforts in general here.)

I think this basic formula (working in some job that is a good fit, while having some amount of balance in your life) is what’s behind a lot of the most important positive events in history to date, and presents possibly historically large opportunities today.

Also relevant are the takeaways from Thomas Kwa's effectiveness as a conjunction of multipliers, in particular:

  • It's more important to have good judgment than to dedicate 100% of your life to an EA project. If output scales linearly with work hours, then you can hit 60% of your maximum possible impact with 60% of your work hours. But if bad judgment causes you to miss one or two multipliers, you could make less than 10% of your maximum impact. (But note that working really hard can sometimes enable multipliers-- see this comment by Mathieu Putz.)
  • Aiming for the minimum of self-care is dangerous.

Amateur hour question, if you don't mind: how does your "future of AI teams" compare/contrast with Drexler's CAIS model?

You might also be interested in Scott's 2010 post warning of the 'next-level trap' so to speak: Intellectual Hipsters and Meta-Contrarianism 

A person who is somewhat upper-class will conspicuously signal eir wealth by buying difficult-to-obtain goods. A person who is very upper-class will conspicuously signal that ey feels no need to conspicuously signal eir wealth, by deliberately not buying difficult-to-obtain goods.

A person who is somewhat intelligent will conspicuously signal eir intelligence by holding difficult-to-understand opinions. A person who is very intelligent will conspicuously signal that ey feels no need to conspicuously signal eir intelligence, by deliberately not holding difficult-to-understand opinions.


Without meaning to imply anything about whether or not any of these positions are correct or not3, the following triads come to mind as connected to an uneducated/contrarian/meta-contrarian divide:

- KKK-style racist / politically correct liberal / "but there are scientifically proven genetic differences"
- misogyny / women's rights movement / men's rights movement
- conservative / liberal / libertarian4
- herbal-spiritual-alternative medicine / conventional medicine / Robin Hanson
- don't care about Africa / give aid to Africa / don't give aid to Africa
- Obama is Muslim / Obama is obviously not Muslim, you idiot / Patri Friedman5

What is interesting about these triads is not that people hold the positions (which could be expected by chance) but that people get deep personal satisfaction from arguing the positions even when their arguments are unlikely to change policy6 - and that people identify with these positions to the point where arguments about them can become personal.

If meta-contrarianism is a real tendency in over-intelligent people, it doesn't mean they should immediately abandon their beliefs; that would just be meta-meta-contrarianism. It means that they need to recognize the meta-contrarian tendency within themselves and so be extra suspicious and careful about a desire to believe something contrary to the prevailing contrarian wisdom, especially if they really enjoy doing so.

In Bostrom's recent interview with Liv Boeree, he said (I'm paraphrasing; you're probably better off listening to what he actually said)

  • p(doom)-related
    • it's actually gone up for him, not down (contra your guess, unless I misinterpreted you), at least when broadening the scope beyond AI (cf. vulnerable world hypothesis, 34:50 in video)
    • re: AI, his prob. dist. has 'narrowed towards the shorter end of the timeline - not a huge surprise, but a bit faster I think' (30:24 in video)
    • also re: AI, 'slow and medium-speed takeoffs have gained credibility compared to fast takeoffs'
    • he wouldn't overstate any of this
  • contrary to people's impression of him, he's always been writing about 'both sides' (doom and utopia) 
  • in the past it just seemed more pressing to him to call attention to 'various things that could go wrong so we could avoid these pitfalls and then we'd have plenty of time to think about what to do with this big future'
    • this reminded me of this illustration from his old paper introducing the idea of x-risk prevention as global priority: 
Load More