For (2), I’m gonna uncharitably rephrase your point as saying: “There hasn’t been a sharp left turn yet, and therefore I’m overall optimistic there will never be a sharp left turn in the future.” Right?
Hm, I wouldn’t have phrased it that way. Point (2) says nothing about the probability of there being a “left turn”, just the speed at which it would happen. When I hear “sharp left turn”, I picture something getting out of control overnight, so it’s useful to contextualize how much compute you have to put in to get performance out, since this suggests that (inasmuch as it’s driven by compute) capabilities ought to grow gradually.
I feel like you’re disagreeing with one of the main arguments of this post without engaging it.
I didn’t mean to disagree with anything in your post, just to add a couple points which I didn’t think were addressed.
You’re right that point (2) wasn’t engaging with the (1-3) triad, because it wasn’t mean to. It’s only about the rate of growth of capabilities (which is important because if each subsequent model is only 10% more capable than the one which came before then there’s good reason to think that alignment techniques which work well on current models will also work on subsequent models).
Again, the big claim of this post is that the sharp left turn has not happened yet. We can and should argue about whether we should feel optimistic or pessimistic about those “wrenching distribution shifts”, but those arguments are as yet untested, i.e. they cannot be resolved by observing today’s pre-sharp-left-turn LLMs. See what I mean?
I do see, and I think this gets at the difference in our (world) models. In a world where there’s a real discontinuity, you’re right, you can’t say much about a post-sharp-turn LLM. In a world where there’s continuous progress, like I mentioned above, I’d be surprised if a “left turn” suddenly appeared without any warning.
Thanks! I still feel like you’re missing my point, let me try again, thanks for being my guinea pig as I try to get to the bottom of it. :)
inasmuch as it’s driven by compute
In terms of the “genome = ML code” analogy (§3.1), humans today have the same compute as humans 100,000 years ago. But humans today have dramatically more capabilities—we have invented the scientific method and math and biology and nuclear weapons and condoms and Fortnite and so on, and we did all that, all by ourselves, autonomously, from scratch. There was no intelligent external non-human entity who was providing humans with bigger brains or new training data or new training setups or new inference setups or anything else.
If you look at AI today, it’s very different from that. LLMs today work better than LLMs from six months ago, but only because there was an intelligent external entity, namely humans, who was providing the LLM with more layers, new training data, new training setups, new inference setups, etc.
…And if you’re now thinking “ohhh, OK, Steve is just talking about AI doing AI research, like recursive self-improvement, yeah duh, I already mentioned that in my first comment” … then you’re still misunderstanding me!
Again, think of the “genome = ML code” analogy (§3.1). In that analogy,
“AIs building better AIs by doing the exact same kinds of stuff that human researchers are doing today to build better AIs”
…would be analogous to…
“Early humans creating more intelligent descendants by doing biotech or selective breeding or experimentally-optimized child-rearing or whatever”.
But humans didn’t do that. We still have basically the same brains as our ancestors 100,000 years ago. And yet humans were still able to dramatically autonomously improve their capabilities, compared to 100,000 years ago. We were making stone tools back then, we’re making nuclear weapons now.
Thus, autonomous learning is a different axis of AI capabilities improvement. It’s unrelated to scaling, and it’s unrelated to “automated AI capabilities research” (as typically envisioned by people in the LLM-sphere). And “sharp left turn” is what I’m calling the transition from “no open-ended autonomous learning” (i.e., the status quo) to “yes open-ended autonomous learning” (i.e., sometime in the future). It’s a future transition, and it has profound implications, and it hasn’t even started (§1.5). It doesn’t have to happen overnight—see §3.7. See what I mean?
Thanks for your patience: I do think this message makes your point clearly. However, I’m sorry to say, I still don’t think I was missing the point. I reviewed §1.5, still believe I understand the open-ended autonomous learning distribution shift, and also find it scary. I also reviewed §3.7, and found it to basically match my model, especially this bit:
Or, of course, it might be more gradual than literally a single run with a better setup. Hard to say for sure. My money would be on “more gradual than literally a single run”, but my cynical expectation is that the (maybe a couple years of) transition time will be squandered
Overall, I don’t have the impression we disagree too much. My guess for what’s going on (and it’s my fault) is that my initial comment’s focus on scaling was not a reaction to anything you said in your post, in fact you didn’t say much about scaling at all. It was more a response to the scaling discussion I see elsewhere.
Hm, I wouldn’t have phrased it that way. Point (2) says nothing about the probability of there being a “left turn”, just the speed at which it would happen. When I hear “sharp left turn”, I picture something getting out of control overnight, so it’s useful to contextualize how much compute you have to put in to get performance out, since this suggests that (inasmuch as it’s driven by compute) capabilities ought to grow gradually.
I didn’t mean to disagree with anything in your post, just to add a couple points which I didn’t think were addressed.
You’re right that point (2) wasn’t engaging with the (1-3) triad, because it wasn’t mean to. It’s only about the rate of growth of capabilities (which is important because if each subsequent model is only 10% more capable than the one which came before then there’s good reason to think that alignment techniques which work well on current models will also work on subsequent models).
I do see, and I think this gets at the difference in our (world) models. In a world where there’s a real discontinuity, you’re right, you can’t say much about a post-sharp-turn LLM. In a world where there’s continuous progress, like I mentioned above, I’d be surprised if a “left turn” suddenly appeared without any warning.
Thanks! I still feel like you’re missing my point, let me try again, thanks for being my guinea pig as I try to get to the bottom of it. :)
In terms of the “genome = ML code” analogy (§3.1), humans today have the same compute as humans 100,000 years ago. But humans today have dramatically more capabilities—we have invented the scientific method and math and biology and nuclear weapons and condoms and Fortnite and so on, and we did all that, all by ourselves, autonomously, from scratch. There was no intelligent external non-human entity who was providing humans with bigger brains or new training data or new training setups or new inference setups or anything else.
If you look at AI today, it’s very different from that. LLMs today work better than LLMs from six months ago, but only because there was an intelligent external entity, namely humans, who was providing the LLM with more layers, new training data, new training setups, new inference setups, etc.
…And if you’re now thinking “ohhh, OK, Steve is just talking about AI doing AI research, like recursive self-improvement, yeah duh, I already mentioned that in my first comment” … then you’re still misunderstanding me!
Again, think of the “genome = ML code” analogy (§3.1). In that analogy,
“AIs building better AIs by doing the exact same kinds of stuff that human researchers are doing today to build better AIs”
…would be analogous to…
“Early humans creating more intelligent descendants by doing biotech or selective breeding or experimentally-optimized child-rearing or whatever”.
But humans didn’t do that. We still have basically the same brains as our ancestors 100,000 years ago. And yet humans were still able to dramatically autonomously improve their capabilities, compared to 100,000 years ago. We were making stone tools back then, we’re making nuclear weapons now.
Thus, autonomous learning is a different axis of AI capabilities improvement. It’s unrelated to scaling, and it’s unrelated to “automated AI capabilities research” (as typically envisioned by people in the LLM-sphere). And “sharp left turn” is what I’m calling the transition from “no open-ended autonomous learning” (i.e., the status quo) to “yes open-ended autonomous learning” (i.e., sometime in the future). It’s a future transition, and it has profound implications, and it hasn’t even started (§1.5). It doesn’t have to happen overnight—see §3.7. See what I mean?
Thanks for your patience: I do think this message makes your point clearly. However, I’m sorry to say, I still don’t think I was missing the point. I reviewed §1.5, still believe I understand the open-ended autonomous learning distribution shift, and also find it scary. I also reviewed §3.7, and found it to basically match my model, especially this bit:
Overall, I don’t have the impression we disagree too much. My guess for what’s going on (and it’s my fault) is that my initial comment’s focus on scaling was not a reaction to anything you said in your post, in fact you didn’t say much about scaling at all. It was more a response to the scaling discussion I see elsewhere.