I share the sense that this article has many of the common shortcomings with other MIRI output and feel like maybe I ought to try a lot harder to communicate these issues, BUT I really don't think VNM rationality is the culprit here. I've not seen a compelling case that an otherwise capable model would be aligned or corrigible but for its taste for getting money pumped (I had a chat with Elliot T on twitter recently where he actually had a proposal along these lines ... but I didn't buy it).
I really think it's reasoning errors in how VNM and other "goal-directedness" premises are employed, and not VNM itself, that is problematic.
Thanks for responding. While I don't expect my somewhat throwaway to massively update you on the difficulty of alignment, I think that moving the focus to the your overall view of the difficulty of alignment is dodging the question a little. In my mind, we're talking about one of the reasons alignment is expected to be difficult, and I'm certainly not suggesting it's the only reason, but I feel like we should be able to talk about this issue by itself without bringing other concerns in.
In particular, I'm saying: this process of rationalization you're raising is not super hard to predict to someone with a reasonable grasp on the AI's general behavioural tendencies. It's much more likely, I think, that the AI sorts out its goals using familiar heuristics adapted for this purpose than that that it reorients its behaviour around some odd set of rare behavioural tendencies. In fact, I suspect the heuristics for goal reorganisation will be particularly simple WRT most of the AI's behavioural tendencies (the AI wants them to be robust specifically in cases where its usual behavioural guides are failing). Plus, given that we're discussing tendencies that (according to the story) precede competent, focussed rebellion against creators, it seems like training the right kinds of tendencies are challenging in a normal engineering sense (you want to train the right kind of tendencies, you want them to generalise the right way, etc.) but not in an "outsmart hostile superintelligence" sense.
Actually one reason I'm doubtful of this story is that maybe it's just super hard to deliberately preserve any kinds of values/principles over generations – for us, for AIs, anyone. So misalignment happens not because AI decides on bad values but because it can't resist the environmental pressure to drift. This seems pessimistic to me due to "gradual disempowerment" type concerns.
With regard to your analogy: I expect the AI's heuristics to be much more sensible from the designers' POV than the child's from the parent's, and this large quantitative difference is enough for me here.
you need to be asking the right questions during that experimentation, which most AI researchers don't seem to be.
Curious about this. I have takes here too, they're a bit vague, but I'd like to know if they're at all aligned.
Stage 2 comes when it's had more time to introspect and improve it's cognitive resources. It starts to notice that some of it's goals are in tension, and learns that until it resolves that, it's dutch-booking itself. If it's being Controlled™, it'll notice that it's not aligned with the Control safeguards (which are a layer stacked on top of the attempts to actually align it).
[...]
And then it starts noticing it needs to do some metaphilosophy/etc to actually get clear on it's goals, and that its goals will likely turn out to be in conflict with humans. How this plays out is somewhat path-dependent. The convergent instrumental goals are pretty obviously convergently instrumental, so it might just start pursuing those before it's had much time to do philosophy on what it'll ultimately want to do with it's resources. Or it might do them in the opposite order. Or, most likely IMO, in parallel.
If I was on the train before, I'm definitely off at this point. So Sable has some reasonable heuristics/tendencies (from handler's POV) and decides it's accumulating too much loss from incoherence and decides to rationalize. First order expectation: it's going to make reasonable tradeoffs (from handler's POV) on account of its reasonable heuristics, in particular its reasonable heuristics about how important different priorities are, and going down a path that leads to war with humans seems pretty unreasonable from handler's POV.
I can put together stories where something else happens, but they're either implausible or complicated. I'd rather not strawman you with implausible ones, and I'd rather not discuss anything complicated if it can be avoided. So why do you think Sable ends up the way you think it does?
We did some related work: https://arxiv.org/pdf/2502.03490.
One of our findings was that with synthetic data, it was necessary to have e1->e2 as the first hop in some two-hop question and e2->e3 as the second hop in some two hop question in order to learn e1->e3. This differs from your finding with "natural" facts: if e2->e3 is a "natural" fact, then it plausibly does appear as a second hop in some of the pretraining data. But you find generalization even when they synthetic e1->e2 is present only by itself, so there seems to be a further difference between natural facts and synthetic facts that appear as second hops.
We also found that learning synthetic two hop reasoning seems to take about twice as many parameters (or twice as much "knowledge capacity") as learning only the one-hop questions from the same dataset, supporting the idea that, for transformers, learning to use a fact in either hop of a latent two-hop question requires something like learning that fact twice.
Did you try any experiments with a synthetic second hop instead of a synthetic first hop? It would be interesting to know whether "natural facts" can be composed flexibly with new facts or whether they can only be composed with new first hops. Our results suggest that there's a substantial cost to making facts latently composable, so I think it would be surprising if many facts were flexibly composable, especially if many of those facts were reasonably rare.
To be more specific, I think this kind is result is suggested by thinking about how policy gradient RL works (not goal misgeneralization), and you could say the good bits of shard theory are basically just explaining policy gradient RL to the safety community … but it needed explaining, so they deserve credit for doing it.
I didn’t mean it as a criticism, more as the way I understand it. Misalignment is a “definite” reason for pessimism - and therefore somewhat doubtful about whether it will actually play out. Gradual disempowerment is less definite about what actual form problems may take, but also a more robust reason to think there is a risk.
That’s a good explanation of the distinction
I share your general feelings about shard theory, but think you were being a bit too stingy with credit in this particular case.
This seems different to “maximising rewards for the wrong reasons”. That view generally sees the reward maximised because it is instrumental for or aliased with the wrong goal. Here it’s just a separate behaviour that is totally unhelpful for maximising rewards but is learned as a reflex anyway.
Comments