I often talk to people who think that if frontier models were egregiously misaligned and powerful enough to pose an existential threat, you could get AI developers to slow down or undeploy models by producing evidence of their misalignment. I'm not so sure. As an extreme thought experiment, I’ll argue this could be hard even if you caught your AI red-handed trying to escape.
Imagine you're running an AI lab at the point where your AIs are able to automate almost all intellectual labor; the AIs are now mostly being deployed internally to do AI R&D. (If you want a concrete picture here, I'm imagining that there are 10 million parallel instances, running at 10x human speed, working 24/7. See e.g. similar calculations here). And suppose (as I...
Crossposted by habryka with Sam's permission. Expect lower probability for Sam to respond to comments here than if he had posted it (he said he'll be traveling a bunch in the coming weeks, so might not have time to respond to anything).
This piece reflects my current best guess at the major goals that Anthropic (or another similarly positioned AI developer) will need to accomplish to have things go well with the development of broadly superhuman AI. Given my role and background, it’s disproportionately focused on technical research and on averting emerging catastrophic risks.
For context, I lead a technical AI safety research group at Anthropic, and that group has a pretty broad and long-term mandate, so I spend a lot of time thinking about what kind of safety...
(Responding in a consolidated way just to this comment.)
Ok, got it. I don't think the US government will be able and willing to coordinate and enforce a worldwide moratorium on superhuman TAI development, if we get to just-barely TAI, at least not without plans that leverage that just-barely TAI in unsafe ways which violate the safety invariants of this plan. It might become more willing than it is now (though I'm not hugely optimistic), but I currently don't think as an institution it's capable of executing on that kind of plan and don't see w... (read more)
I haven't read the Shard Theory work in comprehensive detail. But, fwiw I've read at least a fair amount of your arguments here and not seen anything that bridged the gap between "motivations are made of shards that are contextually activated" and "we don't need to worry about Goodhart and misgeneralization of human at extreme levels of optimization."
I've heard you make this basic argument several times, and my sense is you're pretty frustrated that people still don't seem to have "heard" it properly, or something.
I did feel compelled by your a... (read more)
Previously: Predictions for shard theory mechanistic interpretability results
TL;DR: We algebraically modified the net's runtime goals without finetuning. We also found (what we think is) a "motivational API" deep in...
Often people talk about policies getting "selected for" on the basis of maximizing reward. Then, inductive biases serve as "tie breakers" among the reward-maximizing policies.
Does anyone do this? Under this model the data-memorizing model would basically always win out, which I've never really seen anyone predict. Seems clear that inductive biases do more than tie-breaking.
AI systems up to some high level of intelligence plausibly need to know exactly where they are in space-time in order for deception/"scheming" to make sense as a strategy.
This is because they need to know:
1) what sort of oversight they are subject to
and
2) what effects their actions will have on the real world
(side note: Acausal trade might break this argument)
There are a number of informal proposals to keep AI systems selectively ignorant of (1) and (2) in order to prevent deception. Those proposals seem very promising to flesh out; I'm not aware of any rigorous work doing so, however. Are you?
Are you describing something that would fit within my 'Another type of proposal...' category?
The mistakes can (somewhat) be expressed in the language of Bayesian rationalism by doing two things:
Why not? There a very real and important difference between role playing and systematic scheming. The former isn't ultimately scary or systematic and won't reliably lead to AI takeover; the latter will. If it is indeed systematic scheming, you should be able to generate evidence of that empirically. It will persist in a variety of circumstances where there seems to be an opportunity to seize power, and it won't go away when you change unrelat... (read more)