The weird thing about a portfolio approach is that the things it makes sense to work on in “optimistic scenarios” often trade off against those you’d want to work on in more “pessimistic scenarios,” and I don’t feel like this is really addressed.
Like, if we’re living in an optimistic world where it’s pretty chill to scale up quickly, and things like deception are either pretty obvious or not all that consequential, and alignment is close to default, then sure, pushing frontier models is fine. But if we’re in a world where the problem is nearly impossible, alignment is nowhere close to default, and/or things like deception happen in an abrupt way, then the actions Anthropic is taking (e.g., rapidly scaling models) are really risky.
This is part of what seems weird to me about Anthropic’s safety plan. It seems like the major bet the company is making is that getting empirical feedback from frontier systems is going to help solve alignment. Much of that justification (afaict from the Core Views post) is because Anthropic expects to be surprised by what emerges in larger models. For instance, as this Anthropic paper mentions: models can’t do 3 digit addition basically at all (close to 0% test accuracy) until all of the sudden, as you scale the model slightly, they can (0% to 80% accuracy abruptly). I presume the safety model here is something like: if you can’t make much progress on problems without empirical feedback, and if you can’t get the empirical feedback unless the capability is present to work with, and if capabilities (or their precursors) only emerge at certain scales, then scaling is a bottleneck to alignment progress.
I’m not convinced by those claims, but I think that even if I were, I would have a very different sense of what to do here. Like, it seems to me that our current state of knowledge about how and why specific capabilities emerge (and when they do) is pretty close to “we have no idea.” That means we are pretty close to having no idea about whenand howand why dangerous capabilities might emerge, nor whether they’ll do so continuously or abruptly.
My impression is that Dario agrees with this:
Dwarkesh: “So, dumb it down for me, mechanistically—it doesn’t know addition yet, now it knows addition, what happened?”
Dario: “We don’t know the answer.” (later) “Specific abilities are very hard to predict. When does arithmetic come into place? When do models learn to code? Sometimes it’s very abrupt. It’s kind of like you can predict statistical averages of the weather, but the weather on one particular day is very hard to predict.”
If I put on the “we need empirical feedback from neural nets to make progress on alignment” hat, along with my “prudence” hat, I’m thinking things more like, “okay let’s stop scaling now, and just work really hard on figuring out how exactly capabilities emerged between e.g., GPT-3 and GPT-4. Like, what exactly can we predict about GPT-4 based on GPT-3? Can we break down surprising and abrupt less-scary capabilities into understandable parts, and generalize from that to more-scary capabilities?” Basically, I’m hoping for a bunch more proof of concept that Anthropic is capable of understanding and controlling current systems, before they scale blindly. If they can’t do it now, why should I expect they’ll be able to do it then?
My guess is that a bunch of these concerns are getting swept under the “optimistic scenario” rug, i.e., “sure, maybe we’d do that if we only expected a pessimistic scenario, but we don’t! And in the optimistic scenario, scaling is pretty much fine, and we can grab more probability mass there so we’re choosing to scale and do the safety we can conditioned on that.” I find this dynamic frustrating. The charitable read on having a uniform prior over outcomes is that you’re taking all viewpoints seriously. The uncharitable read is that it gives you enough free parameters and wiggle room to come to the conclusion that “actually scaling is good” no matter what argument someone levies, because you can always make recourse to a different expected world.
Like, even in pessimistic scenarios (where alignment is nearly impossible), Anthropic still concludes they should be scaling in order to “sound the alarm bell,” despite not saying all that much about how that would work, or if it would work, or making any binding commitments, or saying what precautions they’re taking to make sure they would end up in the “sound the alarm bell” world instead of the “now we’re fucked” world, which are pretty close together. Instead they are taking the action “rapidly scaling systems even though we publicly admit to being in a world where it’s unclear how or when or why different capabilities emerge, nor whether they’ll do so abruptly, and we haven’t figured out how to control these systems in the most basic ways.” I don’t understand how Anthropic thinks this is safe.
The safety model for pushing frontier models as much as Anthropic is doing doesn’t make sense to me. If you’re expecting to be surprised by newer models, that’s bad. We should be aiming to not be surprised, so that we have any hope of managing something that might be much smarter and more powerful than us. The other reasons this blog post lists for working on frontier models seem similarly strange to me, although I’ll leave it here for now. From where I’m at, it doesn’t seem like safety concerns really justify pushing frontier models, and I’d like to hear Anthropic defend this claim more, given that they cite it as one of the main reasons they exist:
“A major reason Anthropic exists as an organization is that we believe it’s necessary to do safety research on ‘frontier’ AI systems.”
(I’d honestly like to be convinced this does make sense, if I’m missing something here).
The weird thing about a portfolio approach is that the things it makes sense to work on in “optimistic scenarios” often trade off against those you’d want to work on in more “pessimistic scenarios,” and I don’t feel like this is really addressed.
Like, if we’re living in an optimistic world where it’s pretty chill to scale up quickly, and things like deception are either pretty obvious or not all that consequential, and alignment is close to default, then sure, pushing frontier models is fine. But if we’re in a world where the problem is nearly impossible, alignment is nowhere close to default, and/or things like deception happen in an abrupt way, then the actions Anthropic is taking (e.g., rapidly scaling models) are really risky.
This is part of what seems weird to me about Anthropic’s safety plan. It seems like the major bet the company is making is that getting empirical feedback from frontier systems is going to help solve alignment. Much of that justification (afaict from the Core Views post) is because Anthropic expects to be surprised by what emerges in larger models. For instance, as this Anthropic paper mentions: models can’t do 3 digit addition basically at all (close to 0% test accuracy) until all of the sudden, as you scale the model slightly, they can (0% to 80% accuracy abruptly). I presume the safety model here is something like: if you can’t make much progress on problems without empirical feedback, and if you can’t get the empirical feedback unless the capability is present to work with, and if capabilities (or their precursors) only emerge at certain scales, then scaling is a bottleneck to alignment progress.
I’m not convinced by those claims, but I think that even if I were, I would have a very different sense of what to do here. Like, it seems to me that our current state of knowledge about how and why specific capabilities emerge (and when they do) is pretty close to “we have no idea.” That means we are pretty close to having no idea about when and how and why dangerous capabilities might emerge, nor whether they’ll do so continuously or abruptly.
My impression is that Dario agrees with this:
If I put on the “we need empirical feedback from neural nets to make progress on alignment” hat, along with my “prudence” hat, I’m thinking things more like, “okay let’s stop scaling now, and just work really hard on figuring out how exactly capabilities emerged between e.g., GPT-3 and GPT-4. Like, what exactly can we predict about GPT-4 based on GPT-3? Can we break down surprising and abrupt less-scary capabilities into understandable parts, and generalize from that to more-scary capabilities?” Basically, I’m hoping for a bunch more proof of concept that Anthropic is capable of understanding and controlling current systems, before they scale blindly. If they can’t do it now, why should I expect they’ll be able to do it then?
My guess is that a bunch of these concerns are getting swept under the “optimistic scenario” rug, i.e., “sure, maybe we’d do that if we only expected a pessimistic scenario, but we don’t! And in the optimistic scenario, scaling is pretty much fine, and we can grab more probability mass there so we’re choosing to scale and do the safety we can conditioned on that.” I find this dynamic frustrating. The charitable read on having a uniform prior over outcomes is that you’re taking all viewpoints seriously. The uncharitable read is that it gives you enough free parameters and wiggle room to come to the conclusion that “actually scaling is good” no matter what argument someone levies, because you can always make recourse to a different expected world.
Like, even in pessimistic scenarios (where alignment is nearly impossible), Anthropic still concludes they should be scaling in order to “sound the alarm bell,” despite not saying all that much about how that would work, or if it would work, or making any binding commitments, or saying what precautions they’re taking to make sure they would end up in the “sound the alarm bell” world instead of the “now we’re fucked” world, which are pretty close together. Instead they are taking the action “rapidly scaling systems even though we publicly admit to being in a world where it’s unclear how or when or why different capabilities emerge, nor whether they’ll do so abruptly, and we haven’t figured out how to control these systems in the most basic ways.” I don’t understand how Anthropic thinks this is safe.
The safety model for pushing frontier models as much as Anthropic is doing doesn’t make sense to me. If you’re expecting to be surprised by newer models, that’s bad. We should be aiming to not be surprised, so that we have any hope of managing something that might be much smarter and more powerful than us. The other reasons this blog post lists for working on frontier models seem similarly strange to me, although I’ll leave it here for now. From where I’m at, it doesn’t seem like safety concerns really justify pushing frontier models, and I’d like to hear Anthropic defend this claim more, given that they cite it as one of the main reasons they exist:
(I’d honestly like to be convinced this does make sense, if I’m missing something here).