I’m a computational cognitive scientist studying decision-making and introspection in humans and LLMs. I earned my PhD at Harvard in 2022, and have been a postdoc at Princeton since then.
Adam Morris
Karma: 118
Self-interpretability: LLMs can describe complex internal processes that drive their decisions
Earnest question: For both this & donating to Alex Bores, does it matter whether someone donates sooner rather than a couple months from now? For practical reasons, it will be easier for me to donate in 2026--but if it will have a substantially bigger impact now, then I want to do it sooner.
One small suggestion: When I read this, I genuinely couldn’t tell whether “Gray swans: None detected this week” was a joke (like you were pretending to look for literal gray/black swans), or if it meant something serious. After reading your website, my guess is that it’s meant to be serious—but I’m still not sure, and if it is serious then I don’t know what it means. (My understanding is that “black swan” means an unexpected, highly improbable / out of distribution event, so it wasn’t clear to me what it would mean in this context to be generally looking for global gray/black swans.) Might be worth clarifying or finding other terminology, if you want readers like me to quickly grok what you mean.
We haven’t had one yet! But we only did it ~3 times. Obviously people are more careful than they’d normally be while dancing on the slippery floor.
I’ll add to this list: If you have a kitchen with a tile floor, have everyone take their shoes off, pour soap and water on the floor, and turn it into a slippery sliding dance party. It’s so fun. (My friends and I used to call it “soap kitchen” and it was the highlight of our house parties.)
Printable book of some rationalist creative writing (from Scott A. & Eliezer)
I see, that makes sense. Thank you!
Can you help me see this point? Why not correct it in the dataset? (Assuming that the dataset hasn’t yet been used to train any models)
I’m long overdue here, but thank you so much for doing this!! I’ve been wanting this for a long time and just discovered this post :)
see my comment above—I (ironically) meant aphasia
hahaha I actually also meant aphasia :P
This is ~even more~ anecdotal, but me and several of my friends have noticed increased anosmia since the pandemic, but critically starting before any of us got covid (and including friends who never got it). We conjectured that it could be from some combination of very high stress levels for a long time + social isolation? Just to add some data points to the mix.
[Question] How are you currently modeling COVID contagiousness?
Pretty much all the writing I’ve read by Holocaust survivors says that this was not true, that the experience was unambiguously worse than being dead, and that the only thing that kept them going was the hope of being freed. (E.g. according to Victor Frankl in “Man’s Search for Meaning”, all the prisoners in his camp agreed that, not only was it worse than being dead, it was so bad that any good experiences after being freed could not make up for it how bad it was. Why they didn’t kill themselves is an interesting question that he explores a bit in the book.) Are there any Holocaust survivors who claim otherwise?
Thanks for the thoughtful response, that perspective makes sense. I take your point that ACT-R is unique in the ways you’re describing, and that most cognitive scientists are not working on overarching models of the mind like that. I think maybe our disagreement is about how good/useful of an overarching model ACT-R is? It’s definitely not like in physics, where some overarching theories are widely accepted (e.g. the standard model) even by people working on much more narrow topics—and many of the ones that aren’t (e.g. string theory) are still widely known about and commonly taught. The situation in cog sci (in my view, and I think in many people’s views?) is much more that we don’t have an overarching model of the mind in anywhere close to the level of detail/mechanistic specificity that ACT-R posits, and that any such attempt would be premature/foolish/not useful right now. Like, I think if you polled cognitive scientists, the vast majority would disagree with the title of your post—not because they think there’s a salient alternative, but because they think that there is no theory that even comes close to meriting the title of “best-validated theory of cognition” (even if technically one theory is ahead of the others). Do you know what I mean? Of course, even if most cognitive scientists don’t believe in ACT-R in that way, that alone doesn’t mean that ACT-R is wrong.. I’m curious about the evidence that Terry is talking about above. I just think the field would look really, really different if we actually had a halfway-decent paradigm/overarching model of the mind. And it’s not like ACT-R is some unknown idea that is poised to take over the field once people learn about it. Everyone knew about it in the 90s, and then it fell out of widespread use—and my prior on why that happened is that people weren’t finding it super useful. (Although like I said, I’m really curious to learn more about what Terry/other contemporary people are doing with it!)
No you’re right, it doesn’t say how they should be combined. My assumption—and I suspect the assumption of the authors—is that we have no good widely-accepted overarching model of the mind, and that the best we can agree on is a list of ingredients (and even that list was controversial, e.g. in the commentaries on the paper). I think that’s the reason I, implicitly, was viewing the paper as a contemporary alternative to ACT-R. But I take your point that it’s doing different things.
Thanks for such a thoughtful response Terry :). This all makes a ton of sense—I totally agree that the paper doesn’t give an alternative overarching theory, and that no such alternative theory exists. I guess my high-level worry is that, if ACT-R really were a good overarching model of the mind (like a paradigm, in Kuhnian terms), then it would have become standard or widely accepted in the field in the way that good overarching theories/paradigms became standard in other fields? Coming into this, my thought is that we don’t have any good overarching theory of the mind, and that we just don’t understand the mind well enough to make any models like that. But I am really curious about the success of ACT-R that you’re pointing to. If it’s actually a decent model, why do you think it didn’t take over the field (and shrunk to a small group of continuing researchers)? Genuine question, not rhetorical. My prior is that most cognitive scientists would kill for a good paradigm (I certainly would!).
Long-time lurker, first time commenting. Without necessarily disagreeing on any object-level details, I want to give an alternate perspective. I’m a PhD in computational cog sci, have interacted with most of the top cognitive science departments in the US (e.g. through job search, conferences, etc), and I know literally zero people who use ACT-R for anything. It was never mentioned in any of my grad classes, has never been brought up in any talk I’ve been to—I don’t even know if I’ve even seen it ever cited in a paper I’ve read. I know of it, obviously, and I know that it was super influential back in the 90s, but I’d always just assumed that the research program withered away for some reason (given how little I’d seen it actually being used in top-level research at this point).
This post made me curious how I could have such a different perspective! I don’t know whether academic cognitive science is just really segregated and I’m missing all the ACT-R researchers still out there; whether ACT-R was actually amazing and people have been silly to drop it; whether “top-level” research is misleading and actually the good research is being published in lower-tier journals while flashy fad-based results get published in top journals; or whether ACT-R really did fail for some deep reason. I’ve asked some colleagues why nobody around us uses it anymore, but I haven’t gotten any detailed responses yet.
(Also, this is a small thing, but “fitting human reaction times” is not impressive—that’s a basic feature of many, many models.)
So while I don’t have any object-level disagreements with this post, it feels like helpful context to know that many, many active computational cognitive scientists would strongly disagree that ACT-R is essentially the one best-validated theory of cognition (to the point where they’d be like “huh? what are you talking about?”). This paper gives what I think is a much more contemporary overview of overarching theories of human cognition.
Got it. Okay thanks!