LessWrong 2.0 Reader

[epistemic status: I think I’m mostly right about the main thrust here, but probably some of the specific arguments below are wrong. In the following, I'm much more stating conclusions than providing full arguments. This claim isn’t particularly original to me.]

I’m interested in the following subset of risk from AI:

• Early: That comes from AIs that are just powerful enough to be extremely useful and dangerous-by-default (i.e. these AIs aren’t wildly superhuman).
• Scheming: Risk associated with loss of control to AIs that arises from AIs scheming
  • So e.g. I exclude state actors stealing weights in ways that aren’t enabled by the AIs scheming, and I also exclude non-scheming failure modes. IMO, state actors stealing weights is a serious threat, but non-scheming failure modes aren’t (at this level of capability and dignity).
• Medium dignity [EA · GW]: that is, developers of these AIs are putting a reasonable amount of effort into preventing catastrophic outcomes from their AIs (perhaps they’re spending the equivalent of 10% of their budget on cost-effective measures to prevent catastrophes).
• Nearcasted: no substantial fundamental progress on AI safety techniques, no substantial changes in how AI works.

This subset of risk is interesting because I think it’s a natural scenario at which to target technical work on AI safety. (E.g. it’s the main scenario we’re targeting with our AI control agenda [LW · GW].)

I claim that the majority of this risk comes from the lab using AIs internally to do AI development (by which I mean both research and engineering). This is because the AIs doing AI development naturally require access to compute and model weights that they can potentially leverage into causing catastrophic outcomes—in particular, those resources can be abused to run AIs unmonitored.

Using AIs for AI development looks uniquely risky to me among applications of early-transformative AIs, because unlike all other applications I know about:

• It’s very expensive to refrain from using AIs for this application.
• There’s no simple way to remove affordances from the AI such that it’s very hard for the AI to take a small sequence of actions which plausibly lead quickly to loss of control. In contrast, most other applications of AI probably can be controlled just by restricting their affordances.

If I’m right that the risk from scheming early-transformative models is concentrated onto this pretty specific scenario, it implies a bunch of things:

• It implies that work on mitigating these risks should focus on this very specific setting.
• It implies that AI control is organizationally simpler, because most applications can be made trivially controlled.
• It is pretty plausible to me that AI control is quite easy, because you actually can remove affordances from the AIs that are doing AI R&D such that it’s hard for them to cause problems.

This is a great question, and one of the things I'm most excited about using this framework to study in the future! I have a few ideas but nothing to report yet.

But I will say that I think we should be able to formalize exactly what it would mean for a transformer to create/discover new knowledge, and also to apply the structure from one dataset and apply it to another, or to mix two abstract structures together, etc. I want to have an entire theory of cognitive abilities and the geometric internal structures that support them.

If I'm understanding your question correctly, then the answer is yes, though in practice it might be difficult (I'm actually unsure how computationally intensive it would be, haven't tried anything along these lines yet). This is definitely something to look into in the future!

It's surprising for a few reasons:

• The structure of the points in the simplex is NOT
  • The next token prediction probabilities (ie. the thing we explicitly train the transformer to do)
  • The structure of the data generating model (ie. the thing the good regulator theorem talks about, if I understand the good regulator theorem, which I might not)

The first would be not surprising because it's literally what our loss function asks for, and the second might not be that surprising since this is the intuitive thing people often think about when we say "model of the world." But the MSP structure is neither of those things. It's the structure of inference over the model of the world, which is quite a different beast than the model of the world.

Others might not find it as surprising as I did - everyone is working off their own intuitions.

edit: also I agree with what Kave said about the linear representation.

Launched a few days ago, the plan is:

• Kids tickets are $50
• There's daycare purchasable on-site from 10am to 7pm, for like $10/hour if you book ahead of time or $30/hour if you use it on-the-day
• If you want connection to a nanny for outside of those hours we have a service that can help with that at $45/hour.

Happy to get feedback on this, still figuring out what exactly helps parents and how to set it up right.

Sorry, what? I thought the fear was that we don't know how to make helpful AI at all. (And that people who think they're being helped by seductively helpful-sounding LLM assistants are being misled by surface appearances; the shoggoth underneath has its own desires that we won't like when it's powerful enough to persue them autonomously.) In contrast, this almost makes it sound like you think it is plausible to align AI to its user's intent, but that this would be bad if the users aren't one of "us"—you know, the good alignment researchers who want to use AI to take over the universe, totally unlike those evil capabilities researchers who want to use AI to produce economically valuable goods and services.

My steelman of this (though to be clear I think your comment makes good points): 

There is a large difference between a system being helpful and a system being aligned. Ultimately AI existential risk is a coordination problem where I expect catastrophic consequences because a bunch of people want to build AGI without making it safe. Therefore making technologies that in a naive and short-term sense just help AGI developers build whatever they want to build will have bad consequences. If I trusted everyone to use their intelligence just for good things, we wouldn't have anthropogenic existential risk on our hands.

Some of those technologies might end up useful for also getting the AI to be more properly aligned, or maybe to help with work that reduces the risk of AI catastrophe some other way, though my current sense is that kind of work is pretty different and doesn't benefit remotely as much from generically locally-helpful AI.

In-general I feel pretty sad about conflating "alignment" with "short-term intent alignment". I think the two problems are related but have really important crucial differences, I don't think the latter generalizes that well to the former (for all the usual sycophancy/treacherous-turn reasons), and indeed progress on the latter IMO mostly makes the world marginally worse because the thing it is most likely to be used for is developing existentially dangerous AI systems faster.

Edit: Another really important dimension to model here is also not just the effect of that kind of research on what individual researchers will do, but what effect this kind of research will have on what the market wants to invest in. My standard story of doom is centrally rooted in there being very strong short-term economic incentives to build more capable AGI for any individual, enabling people to make billions to trillions of dollars, while the downside risk is a distributed negative externality that is not at all priced into the costs of AI development. Developing applications of AI that make a lot of money without accounting for the negative extinction externalities therefore can be really quite bad for the world. 

If people don’t publish their findings and make contributions in public, how are they supposed to establish themselves as researchers in the first place?

Fixed. Thanks.

Oh, I wasn't saying that student debt is variable interest, just making a point about debt and inflation in general.

I'm very sympathetic to the idea of being very careful about publishing things that could spread capabilities ideas. However, I think there are several important things missing from your world model, which cause me to believe that following your advice would substantially hurt alignment progress.

(To be clear, none of this applies to alignment people working directly on capabilities, who should, like, not. Rather, this is about alignment researchers accidentally advancing capabilities by talking to capabilities people)

• It's genuinely hard to come up with ideas that help capabilities a lot. I think you are severely underestimating how hard it is, and how much insight is required. I think one issue here is that most papers on arxiv are garbage and don't actually make any progress, but those papers are not the ones that are pushing AGI forward anyways.
• Even if you try very hard to do so, it's still very hard to convince people that you're right if you don't have a ton of clout via a legible reputation of being right a lot. Everyone has an agenda they're convinced will solve AGI and is too busy trying to convince everyone else to work on their agenda.
• High level ideas are generally not that valuable in and of themselves. People generally learn to ignore ideas unless they have strong empirical evidence of correctness (or endorsement of highly respected researchers) because there are simply too many ideas. The valuable thing is not the idea itself, but the knowledge of which ideas are actually correct.
• I think deeply understanding top tier capabilities researchers' views on how to achieve AGI is actually extremely valuable for thinking about alignment. Even if you disagree on object level views, understanding how very smart people come to their conclusions is very valuable.
• I think alignment discourse is greatly harmed by people being too scared to say things. When it bleeds over to being too scared to think about capabilities related topics for fear of accidentally generating something dangerous, I think this is even more harmful.