By default, humans only care about variables they could (in principle) easily optimize or comprehend.
I think this is incorrect. I think humans have values which are essentially provisional. In other words, they're based on pointers which are supposed to be impossible to fully dereference. Examples:
- Friendship--pointing at another mind, who you never fully comprehend, who can always surprise you--which is part of the point
- Boredom / fun--pointing at surprise, novelty, diagonalizing against what you already understand
1See Jessica's comment. Yeah it's primitive recursive assuming that your deductive process is primitive recursive. (Also assuming that your traders are primitive recursive; e.g. if they are polytime as in the paper.) There's probably some other parameters not necessarily set in the implementation described in the paper, e.g. the enumerator of trader-machines, but you can make those primrec.
1(Interesting. FWIW I've recently been thinking that it's a mistake to think of this type of thing--"what to do after the acute risk period is safed"--as being a waste of time / irrelevant; it's actually pretty important, specifically because you want people trying to advance AGI capabilities to have an alternative, actually-good vision of things. A hypothesis I have is that many of them are in a sense genuinely nihilistic/accelerationist; "we can't imagine the world after AGI, so we can't imagine it being good, so it cannot be good, so there is no such thing as a good future, so we cannot be attached to a good future, so we should accelerate because that's just what is happening".)
really smart people
Differences between people are less directly revelative of what's important in human intelligence. My guess is that all or very nearly all human children have all or nearly all the intelligence juice. We just, like, don't appreciate how much a child is doing in constructing zer world.
the current models have basically all the tools a moderately smart human have, with regards to generating novel ideas
Why on Earth do you think this? (I feel like I'm in an Asch Conformity test, but with really really high production value. Like, after the experiment, they don't tell you what the test was about. They let you take the card home. On the walk home you ask people on the street, and they all say the short line is long. When you get home, you ask your housemates, and they all agree, the short line is long.)
I don't see what's missing that a ton of training on a ton of diverse, multimodal tasks + scaffoldin + data flywheel isn't going to figure out.
My response is in the post.
I'm curious if you have a sense from talking to people.
More recently I've mostly disengaged (except for making kinda-shrill LW comments). Some people say that "concepts" aren't a thing, or similar. E.g. by recentering on performable tasks, by pointing to benchmarks going up and saying that the coarser category of "all benchmarks" or similar is good enough for predictions. (See e.g. Kokotajlo's comment here https://www.lesswrong.com/posts/oC4wv4nTrs2yrP5hz/what-are-the-strongest-arguments-for-very-short-timelines?commentId=QxD5DbH6fab9dpSrg, though his actual position is of course more complex and nuanced.) Some people say that the training process is already concept-gain-complete. Some people say that future research, such as "curiosity" in RL, will solve it. Some people say that the "convex hull" of existing concepts is already enough to set off FURSI (fast unbounded recursive self-improvement).
(though I feel confused about how to update on the conjunction of those, and the things LLMs are good at — all the ways they don't behave like a person who doesn't understand X, either, for many X.)
True; I think I've heard some various people discussing how to more precisely think of the class of LLM capabilities, but maybe there should be more.
if that's less sample-efficient than what humans are doing, it's not apparent to me that it can't still accomplish the same things humans do, with a feasible amount of brute force
It's often awkward discussing these things, because there's sort of a "seeing double" that happens. In this case, the "double" is:
"AI can't FURSI because it has poor sample efficiency...
- ...and therefore it would take k orders of magnitude more data / compute than a human to do AI research."
- ...and therefore more generally we've not actually gotten that much evidence that the AI has the algorithms which would have caused both good sample efficiency and also the ability to create novel insights / skills / etc."
The same goes mutatis mutandis for "can make novel concepts".
I'm more saying 2. rather than 1. (Of course, this would be a very silly thing for me to say if we observed the gippities creating lots of genuine novel useful insights, but with low sample complexity (whatever that should mean here). But I would legit be very surprised if we soon saw a thing that had been trained on 1000x less human data, and performs at modern levels on language tasks (allowing it to have breadth of knowledge that can be comfortably fit in the training set).)
can't still accomplish the same things humans do
Well, I would not be surprised if it can accomplish a lot of the things. It already can of course. I would be surprised if there weren't some millions of jobs lost in the next 10 years from AI (broadly, including manufacturing, driving, etc.). In general, there's a spectrum/space of contexts / tasks, where on the one hand you have tasks that are short, clear-feedback, and common / stereotyped, and not that hard; on the other hand you have tasks that are long, unclear-feedback, uncommon / heterogenous, and hard. The way humans do things is that we practice the short ones in some pattern to build up for the variety of long ones. I expect there to be a frontier of AIs crawling from short to long ones. I think at any given time, pumping in a bunch of brute force can expand your frontier a little bit, but not much, and it doesn't help that much with more permanently ratcheting out the frontier.
AI that's narrowly superhuman on some range of math & software tasks can accelerate research
As you're familiar with, if you have a computer program that has 3 resources bottlenecks A (50%), B (25%), and C (25%), and you optimize the fuck out of A down to ~1%, you ~double your overall efficiency; but then if you optimize the fuck out of A again down to .1%, you've basically done nothing. The question to me isn't "does AI help a significant amount with some aspects of AI research", but rather "does AI help a significant and unboundedly growing amount with all aspects of AI research, including the long-type tasks such as coming up with really new ideas".
AI is transformative enough to motivate a whole lot of sustained attention on overcoming its remaining limitations
This certainly makes me worried in general, and it's part of why my timelines aren't even longer; I unfortunately don't expect a large "naturally-occurring" AI winter.
seems bizarre if whatever conceptual progress is required takes multiple decades
Unfortunately I haven't addressed your main point well yet... Quick comments:
- Strong minds are the most structurally rich things ever. That doesn't mean they have high algorithmic complexity; obviously brains are less algorithmically complex than entire organisms, and the relevant aspects of brains are presumably considerably simpler than actual brains. But still, IDK, it just seems weird to me to expect to make such an object "by default" or something? Craig Venter made a quasi-synthetic lifeform--but how long would it take us to make a minimum viable unbounded invasive organic replicator actually from scratch, like without copying DNA sequences from existing lifeforms?
- I think my timelines would have been considered normalish among X-risk people 15 years ago? And would have been considered shockingly short by most AI people.
- I think most of the difference is in how we're updating, rather than on priors? IDK.
It's a good question. Looking back at my example, now I'm just like "this is a very underspecified/confused example". This deserves a better discussion, but IDK if I want to do that right now. In short the answer to your question is
- I at least would not be very surprised if gippity-seek-o5-noAngular could do what I think you're describing.
- That's not really what I had in mind, but I had in mind something less clear than I thought. The spirit is about "can the AI come up with novel concepts", but the issue here is that "novel concepts" are big things, and their material and functioning and history are big and smeared out.
I started writing out a bunch of thoughts, but they felt quite inadequate because I knew nothing about the history of the concept of angular momentum; so I googled around a tiny little bit. The situation seems quite awkward for the angular momentum lesion experiment. What did I "mean to mean" by "scrubbed all mention of stuff related to angular momentum"--presumably this would have to include deleting all subsequent ideas that use angular moment in their definitions, but e.g. did I also mean to delete the notion of cross product?
It seems like angular momentum was worked on in great detail well before the cross product was developed at all explicitly. See https://arxiv.org/pdf/1511.07748 and https://en.wikipedia.org/wiki/Cross_product#History. Should I still expect gippity-seek-o5-noAngular to notice the idea if it doesn't have the cross product available? Even if not, what does and doesn't this imply about this decade's AI's ability to come up with novel concepts?
(I'm going to mull on why I would have even said my previous comment above, given that on reflection I believe that "most" concepts are big and multifarious and smeared out in intellectual history. For some more examples of smearedness, see the subsection here: https://tsvibt.blogspot.com/2023/03/explicitness.html#the-axiom-of-choice)
(Still impressive and interesting of course, just not literally SOTA.)
1According to the article, SOTA was <1% of cells converted into iPSCs
I don't think that's right, see https://www.cell.com/cell-stem-cell/fulltext/S1934-5909(23)00402-2
But like, I wouldn't be surprised if, say, someone trained something that performed comparably to LLMs on a wide variety of benchmarks, using much less "data"... and then when you look into it, you find that what they were doing was taking activations of the LLMs and training the smaller guy on the activations. And I'll be like, come on, that's not the point; you could just as well have "trained" the smaller guy by copy-pasting the weights from the LLM and claimed "trained with 0 data!!". And you'll be like "but we met your criterion!" and I'll just be like "well whatever, it's obviously not relevant to the point I was making, and if you can't see that then why are we even having this conversation". (Or maybe you wouldn't do that, IDK, but this sort of thing--followed by being accused of "moving the goal posts"--is why this question feels frustrating to answer.)
Um, ok fine, so what alternative term do you propose to replace "pre-paradigmatic" as it is currently used, to indicate that there's no remotely satisfactory paradigm in which to get going on the parts of the field-to-be that really matter?