All of Stuart_Armstrong's Comments + Replies

Not at all what I'm angling at. There's a mechanistic generator for why humans navigate ontology shifts well (on my view). Learn about the generators, don't copy the algorithm.

I agree that humans navigate "model splinterings" quite well. But I actually think the algorithm might be more important than the generators. The generators comes from evolution and human experience in our actual world; this doesn't seem like it would generalise. The algorithm itself, though, may very generalisable (potential analogy: humans have instinctive grasp of all numbers u... (read more)

Do you predict that if I had access to a range of pills which changed my values to whatever I wanted, and I could somehow understand the consequences of each pill (the paperclip pill, the yay-killing pill, ...), I would choose a pill such that my new values would be almost completely unaligned with my old values?

This is the wrong angle, I feel (though it's the angle I introduced, so apologies!). The following should better articulate my thoughts:

We have an AI-CEO money maximiser, rewarded by the stock price ticker as a reward function. As long as the AI... (read more)

It is not that human values are particularly stable. It's that humans themselves are pretty limited. Within that context, we identify the stable parts of ourselves as "our human values".

If we lift that stability - if we allow humans arbitrary self-modification and intelligence increase - the parts of us that are stable will change, and will likely not include much of our current values. New entities, new attractors.

Hey, thanks for posting this!

And I apologise - I seem to have again failed to communicate what we're doing here :-(

"Get the AI to ask for labels on ambiguous data"

Having the AI ask is a minor aspect of our current methods, that I've repeatedly tried to de-emphasise (though it does turn it to have an unexpected connection with interpretability). What we're trying to do is:

1. Get the AI to generate candidate extrapolations of its reward data, that include human-survivable candidates.
2. Select among these candidates to get a human-survivable ultimate reward

The aim of this post is not to catch out GPT-3; it's to see what concept extrapolation could look like for a language model.

To see this, imagine the AUP agent builds a subagent to make $Q_R^{\ast }(s,a)\approx Q_R^{\ast }(s,\varnothing )$ for all future $s,a$, in order to neutralize the penalty term. This means it can't make the penalty vanish without destroying its ability to better optimize its primary reward, as the (potentially catastrophically) powerful subagent makes sure the penalty term stays neutralized.

I believe this is incorrect. The $a$ and $\varnothing$ are the actions of the AUP agent. The subagent just needs to cripple the AUP agent so that all actions are equivalent, then go about maximising $R$ to the upmost.

Hey there! Sorry for the delay. $50 awarded to you for fastest good reference. PM me your bank details.

I'm not sure why you picked $n/2$.

Because it's the first case I thought of where the probability numbers work out, and I just needed one example to round off the post :-)

It's worth you write up your point and post it - that tends to clarify the issue, for yourself as well as for others.

I've posted on the theoretical difficulties of aggregating the utilities of different agents. But doing it in practice is much more feasible (scale the utilities to some not-too-unreasonable scale, add them, maximise sum).

But value extrapolation is different from human value aggregation; for example, low power (or low impact) AIs can be defined with value extrapolation, and that doesn't need human value aggregation.

Bedankt!

Yes, those are important to provide, and we will.

I do not put too much weight on that intuition, except as an avenue to investigate (how do humans do it, exactly? If it depends on the social environment, can the conditions of that be replicated?).

We're aiming to solve the problem in a way that is acceptable to one given human, and then generalise from that.

CEV is based on extrapolating the person; the values are what the person would have had, had they been smarter, known more, had more self-control, etc... Once you have defined the idealised person, the values emerge as a consequence. I've criticised this idea in the past, mainly because the process to generate the idealised person seems vulnerable to negative attractors (Eliezer's most recent version of CEV has less of this problem).

Value extrapolation and model splintering are based on extrapolating features and concepts in models, to other models. This c... (read more)

UK based currently, Rebecca Gorman other co-founder.

Firstly, because the problem feels central to AI alignment, in the way that other approaches didn't. So making progress in this is making general AI alignment progress; there won't be such a "one error detected and all the work is useless" problem. Secondly, we've had success generating some key concepts, implying the problem is ripe for further progress.

Thanks!

It's an interesting question as to whether aAlice is actually overconfident. Her predictions about human behaviour may be spot on, at this point - much better than human predictions about ourselves. So her confidence depends on whether she has the right kind of philosophical uncertainty.

Developing this idea a bit: https://www.lesswrong.com/posts/kMJxwCZ4mc9w4ezbs/how-an-alien-theory-of-mind-might-be-unlearnable

I actually don't think that Alice could help a (sufficiently alien) alien. She needs an alien theory of mind to understand what the alien wants, how they would extrapolate, how to help that extrapolation without manipulating it, and so on. Without that, she's just projecting human assumptions in alien behaviour and statements.

Thanks for the link.

Yes, but we would be mostly indifferent to shifts in the distribution that preserve most of the features - eg if the weather was the same but delayed or advanced by six days.

I have some draft posts explaining some of this stuff better, I can share them privately, or hang on another month or two. :)

I'd like to see them. I'll wait for the final (posted) versions, I think.

More detailed response: https://www.lesswrong.com/posts/DjTKMEwRqpuKkJzTo/are-there-alternative-to-solving-value-transfer-and

More detailed response: https://www.lesswrong.com/posts/DjTKMEwRqpuKkJzTo/are-there-alternative-to-solving-value-transfer-and

Because our preferences are inconsistent, and if an AI says "your true preferences are $U_H$", we're likely to react by saying "no! No machine will tell me what my preferences are. My true preferences are $U_H^{\prime }$, which are different in subtle ways".

Thanks for developing the argument. This is very useful.

The key point seems to be whether we can develop an AI that can successfully behave as a low impact AI - not as a "on balance, things are ok", but a genuinely low impact AI that ensure that we don't move towards a world where our preference might be ambiguous or underdefined.

But consider the following scenario: the AGI knows that, as a consequence of its actions, one AGI design will be deployed rather than another. Both of these designs will push the world into uncharted territory. How should it deal with that situation?

The successor problem is important, but it assumes we have the values already.

I'm imagining algorithms designing successors with imperfect values (that they know to be imperfect). It's a somewhat different problem (though solving the classical successor problem is also important).

I agree there are superintelligent unconstrained AIs that can accomplish tasks (making a cup of tea) without destroying the world. But I feel it would have to have so much of human preferences already (to compute what is and what isn't an acceptable tradeoff in making you your cup of tea) that it may as well be fully aligned anyway - very little remains to define full alignment.

Thanks! Lots of useful thoughts here.

Cool, thanks; already in contact with them.

Those are very relevant to this project, thanks. I want to see how far we can push these approaches; maybe some people you know would like to take part?

Vertigo, lust, pain reactions, some fear responses, and so on, don't involve a model. Some versions of "learning that it's cold outside" don't involve a model, just looking out and shivering; the model aspect comes in when you start reasoning about what to do about it. People often drive to work without consciously modelling anything on the way.

Think model-based learning versus Q-learning. Anything that's more Q-learning is not model based.

I think the question of whether any particular plastic synapse is or is not part of the information content of the model will have a straightforward yes-or-no answer.

I don't think it has an easy yes or no answer (at least without some thought as to what constitutes a model within the mess of human reasoning) and I'm sure that even if it does, it's not straightforward.

since we probably won't have those kinds of real-time-brain-scanning technologies, right?

One hope would be that, by the time we have those technologies, we'd know what to look for.

I have only very limited access to GPT-3; it would be interesting if others played around with my instructions, making them easier for humans to follow, while still checking that GPT-3 failed.

Thanks!

More SIAish for conventional anthropic problems. Other theories are more applicable for more specific situations, specific questions, and for duplicate issues.

Cheers, these are useful classifications.

The idea that maximising the proxy will inevitably end up reducing the true utility seems a strong implicit part of Goodharting the way it's used in practice.

After all, if the deviation is upwards, Goodharting is far less of a problem. It's "suboptimal improvement" rather than "inevitable disaster".

I want a formalism capable of modelling and imitating how humans handle these situations, and we don't usually have dynamic consistency (nor do boundedly rational agents).

Now, I don't want to weaken requirements "just because", but it may be that dynamic consistency is too strong a requirement to properly model what's going on. It's also useful to have AIs model human changes of morality, to figure out what humans count as values, so getting closer to human reasoning would be necessary.

Hum... how about seeing enforcement of dynamic consistency as having a complexity/computation cost, and Dutch books (by other agents or by the environment) providing incentives to pay the cost? And hence the absence of these Dutch books meaning there is little incentive to pay that cost?

Desideratum 1: There should be a sensible notion of what it means to update a set of environments or a set of distributions, which should also give us dynamic consistency.

I'm not sure how important dynamic consistency should be. When I talk about model splintering, I'm thinking of a bounded agent making fundamental changes to their model (though possibly gradually), a process that is essentially irreversible and contingent the circumstance of discovering new scenarios. The strongest arguments for dynamic consistency are the Dutch-book type arguments, wh... (read more)

For real humans, I think this is a more gradual process - they learn and use some distinctions, and forget others, until their mental models are quite different a few years down the line.

The splintering can happen when a single feature splinters; it doesn't have to be dramatic.

Thanks. I think we mainly agree here.

Look at the paper linked for more details ( https://arxiv.org/abs/1712.05812 ).

Basically "humans are always fully rational and always take the action they want to" is a full explanation of all of human behaviour, that is strictly simpler than any explanation which includes human biases and bounded rationality.

But if you are expecting a 100% guarantee that the uncertainty metrics will detect every possible bad situation

I'm more thinking of how we could automate the navigating of these situations. The detection will be part of this process, and it's not a Boolean yes/no, but a matter of degree.

I agree that once you have landed in the bad situation, mitigation options might be much the same, e.g. switch off the agent.

I'm most interested in mitigation options the agent can take itself, when it suspects it's out-of-distribution (and without being turned off, ideally).

Thanks! Lots of useful insights in there.

So I might classify moving out-of-distribution as something that happens to a classifier or agent, and model splintering as something that the machine learning system does to itself.

Why do you think it's important to distinguish these two situations? It seems that the insights for dealing with one situation may apply to the other, and vice versa.

Cheers! My opinion on category theory has changed a bit, because of this post; by making things fit into the category formulation, I developed insights into how general relations could be used to connect different generalised models.