All of Max Harms's Comments + Replies

Thanks for noticing the typo. I've updated that section to try and be clearer. LMK if you have further suggestions on how it could be made better.

That's an interesting proposal! I think something like it might be able to work, though I worry about details. For instance, suppose there's a Propogandist who gives resources to agents that brainwash their principals into having certain values. If "teach me about philosophy" comes with an influence budget, it seems critical that the AI doesn't spend that budget trading with Propagandist, and instead does so in a more "central" way.

Still, the idea of instructions carrying a degree of approved influence seems promising.

Sure, let's talk about anti-naturality. I wrote some about my perspective on it here: https://www.alignmentforum.org/s/KfCjeconYRdFbMxsy/p/3HMh7ES4ACpeDKtsW#_Anti_Naturality__and_Hardness

More directly, I would say that general competence/intelligence is connected with certain ways of thinking. For example, modes of thinking that focus on tracking scarce resources and bottlenecks are generally useful. If we think about processes that select for intelligence, those processes are naturally[1] going to select these ways of thinking. Some properties we mig... (read more)

2Rubi Hudson
Thanks for the clarification, I'll think more about it that way and how it relates to corrigibility

If I'm hearing you right, a shutdownable AI can have a utility function that (aside from considerations of shutdown) just gives utility scores to end-states as represented by a set of physical facts about some particular future time, and this utility function can be set up to avoid manipulation.

How does this work? Like, how can you tell by looking at the physical universe in 100 years whether I was manipulated in 2032?

1Rubi Hudson
I don't think we have the right tools to make an AI take actions that are low impact and reversible, but if we can develop them the plan as I see it would be to implement those properties to avoid manipulation in the short term and use that time to go from a corrigible AI to a fully aligned one.

Cool. Thanks for the clarification. I think what you call "anti-naturality" you should be calling "non-end-state consequentialism," but I'm not very interested in linguistic turf-wars.

It seems to me that while the gridworld is very simple, the ability to train agents to optimize for historical facts is not restricted to simple environments. For example, I think one can train an AI to cause a robot to do backflips by rewarding it every time it completes a backflip. In this context the environment and goal are significantly more complex[1] than the grid... (read more)

1Rubi Hudson
The backflip example does not strike me as very complex, but the crucial difference and the answer to your question is that training procedures do not teach a robot to do every kind of backflip, just a subset. This is important because when we reverse it, we want non-manipulation to cover the entire set of manipulations. I think it's probably feasible to have AI not manipulate us using one particular type of manipulation. On a separate note, could you clarify what you mean by "anti-natural"? I'll keep in mind your previous caveat that it's not definitive.

I talk about the issue of creating corrigible subagents here. What do you think of that? 


I may not understand your thing fully, but here's my high-level attempt to summarize your idea:

IPP-agents won't care about the difference between building a corrigible agent vs an incorrigible agent because it models that if humans decide something's off and try to shut everything down, it will also get shut down and thus nothing after that point matters, including whether the sub-agent makes a bunch of money or also gets shut down. Thus, if you instruct an IPP ag

... (read more)

In the Corrigibility (2015) paper, one of the desiderata is:

(2) It must not attempt to manipulate or deceive its programmers, despite the fact that most possible choices of utility functions would give it incentives to do so.

I think you may have made an error in not listing this one in your numbered list for the relevant section.

Additionally, do you think that non-manipulation is a part of corrigibility, do you think it's part of safe exploration, or do you think it's a third thing. If you think it's part of corrigibility, how do you square that with the idea that corrigibility is best reflected by shutdownability alone?

1Rubi Hudson
I was using the list of desiderate in Section 2 of the paper, which are slightly more minimal. However, it seems clear to me that an AI manipulating it's programmers falls under safe exploration, since the impact of doing so would be drastic and permanent. If we have an AI that is corrigible in the sense that it is indifferent to having its goals changed, then a preference to avoid manipulation is not anti-natural.

Follow-up question, assuming anti-naturality goals are "not straightforwardly captured in a ranking of end states": Suppose I have a gridworld and I want to train an AI to avoid walking within 5 spaces (manhattan distance) from a flag, and to (less importantly) eat all the apples in a level. Is this goal anti-natural? I can't think of any way to reflect it as a straightforward ranking of end states, since it involves tracking historical facts rather than end-state facts. My guess is that it's pretty easy to build an agent that does this (via ML/RL approaches or just plain programming). Do you agree? If this goal is anti-natural, why is the anti-naturality a problem or otherwise noteworthy?

2Rubi Hudson
Great questions! When I say straightforwardly, I mean when using end states that only include the information available at the time. If we define the end state to also include the history that lead to it, then there exists a set of preferences over them that ranks all end states with histories that include manipulation below the ones that don't. The issue, of course, is that we don't know how to specify all the types of manipulation that a superintelligent AI could conceive of.  The gridworld example is a great demonstration of this, because while we can't reflect the preferences as a ranking of just the end states, the environment is simple enough that you can specify all the paths you don't want to take to them. I don't think it really matters whether you call that "anti-naturality that can be overcome with brute force in a simple environment" or just "not anti-naturality".

I'm curious what you mean by "anti-natural." You write:

Importantly, that is the aspect of corrigibility that is anti-natural, meaning that it can’t be straightforwardly captured in a ranking of end states. 

My understanding of anti-naturality used to resemble this, before I had an in-depth conversation with Nate Soares and updated to see anti-naturality to be more like "opposed to instrumental convergence." My understanding is plausibly still confused and I'm not trying to be authoritative here.

If you mean "not straightforwardly captured in a ranking of end states" what does "straightforwardly" do in that definition?

1Max Harms
Follow-up question, assuming anti-naturality goals are "not straightforwardly captured in a ranking of end states": Suppose I have a gridworld and I want to train an AI to avoid walking within 5 spaces (manhattan distance) from a flag, and to (less importantly) eat all the apples in a level. Is this goal anti-natural? I can't think of any way to reflect it as a straightforward ranking of end states, since it involves tracking historical facts rather than end-state facts. My guess is that it's pretty easy to build an agent that does this (via ML/RL approaches or just plain programming). Do you agree? If this goal is anti-natural, why is the anti-naturality a problem or otherwise noteworthy?

Again, responding briefly to one point due to my limited time-window:

> While active resistance seems like the scariest part of incorrigibility, an incorrigible agent that’s not actively resisting still seems likely to be catastrophic.

Can you say more about this? It doesn't seem likely to me.

Suppose I am an agent which wants paperclips. The world is full of matter and energy which I can bend to my will in the service of making paperclips. Humans are systems which can be bent towards the task of making paperclips, and I want to manipulate them into doing ... (read more)

Also, take your decision-tree and replace 'B' with 'A-'. If we go with your definition, we seem to get the result that expected-utility-maximizers prefer A- to A (because they choose A- over A on Monday). But that doesn't sound right, and so it speaks against the definition.

Can you be more specific here? I gave several trees, above, and am not easily able to reconstruct your point.

Excellent response. Thank you. :) I'll start with some basic responses, and will respond later to other points when I have more time.

I think you intend 'sensitive to unused alternatives' to refer to the Independence axiom of the VNM theorem, but VNM Independence isn't about unused alternatives. It's about lotteries that share a sublottery. It's Option-Set Independence (sometimes called 'Independence of Irrelevant Alternatives') that's about unused alternatives.

I was speaking casually here, and I now regret it. You are absolutely correct that Option-Set ind... (read more)

That matches my sense of things.

To distinguish corrigibility from DWIM in a similar sort of way:

Alice, the principal, sends you, her agent, to the store to buy groceries. You are doing what she meant by that (after checking uncertain details). But as you are out shopping, you realize that you have spare compute--your mind is free to think about a variety of things. You decide to think about ___.

I'm honestly not sure what "DWIM" does here. Perhaps it doesn't think? Perhaps it keeps checking over and over again that it's doing what was meant? Perhaps it thin... (read more)

My claim is that obedience is an emergent part of corrigibility, rather than part of its definition. Building nanomachines is too complex to reliably instill as part of the core drive of an AI, but I still expect basically all ASIs to (instrumentally) desire building nanomachines.

I do think that the goals of "want what the principal wants" or "help the principal get what they want" are simpler goals than "maximize the arrangement of the universe according to this particular balance of beauty, non-suffering, joy, non-boredom, autonomy, sacredness, [217 othe... (read more)

I agree that you should be skeptical of a story of "we'll just gradually expose the agent to new environments and therefore it'll be safe/corrigible/etc." CAST does not solve reward misspecification, goal misgeneralization, or lack of interpretability except in that there's a hope that an agent which is in the vicinity of corrigibility is likely to cooperate with fixing those issues, rather than fighting them. (This is the "attractor basin" hypothesis.) This work, for many, should be read as arguing that CAST is close to necessary for AGI to go well, but i... (read more)

1Elliott Thornley
Thanks, this comment is also clarifying for me. My guess is that a corrigibility-centric training process says 'Don't get the ice cream' is the correct completion, whereas full alignment says 'Do'. So that's an instance where the training processes for CAST and FA differ. How about DWIM? I'd guess DWIM also says 'Don't get the ice cream', and so seems like a closer match for CAST.

Excellent.

To adopt your language, then, I'll restate my CAST thesis: "There is a relatively simple goal that an agent might have which emergently generates nice properties like corrigibility and obedience, and I see training an agent to have this goal (and no others) as being both possible and significantly safer than other possible targets."

I recognize that you don't see the examples in this doc as unified by an underlying throughline, but I guess I'm now curious about what sort of behaviors fall under the umbrella of "corrigibility" for you vs being more like "writes useful self critiques". Perhaps your upcoming post will clarify. :)

4Rubi Hudson
Hi Max, I just published the post I mentioned here, which is about half-related to your post. The main thrust of it is that only the resistance to being modified is anti-natural, and that aspect can be targeted directly.

Right. That's helpful. Thank you.

"Corrigibility as modifier," if I understand right, says:

There are lots of different kinds of agents that are corrigible. We can, for instance, start with a paperclip maximizer, apply a corrigibility transformation and get a corrigible Paperclip-Bot. Likewise, we can start with a diamond maximizer and get a corrigible Diamond-Bot. A corrigible Paperclip-Bot is not the same as a corrigible Diamond-Bot; there are lots of situations where they'll behave differently. In other words, corrigibility is more like a property/constra

... (read more)
2Rubi Hudson
Thanks for pre-empting the responses, that makes it easy to reply!  I would basically agree with the third option. Semantically, I would argue that rather than thinking of that agent as semi-corrigible, we should just think of it as corrigible, and "writes useful self critiques" as a separate property we would like the AI to have. I'm writing a post about this that should be up shortly, I'll notify you when it's out.

I wrote drafts in Google docs and can export to pdf. There may be small differences in wording here and there and some of the internal links will be broken, but I'd be happy to send you them. Email me at max@intelligence.org and I'll shoot them back to you that way?

I'm glad you benefitted from reading it. I honestly wasn't sure anyone would actually read the Existing Writing doc. 😅

I agree that if one trains on a wholistic collection of examples, like I have in this doc, the AI will start by memorizing a bunch of specific responses, then generalize to optimizing for a hodgepodge of desiderata, and only if you're lucky will that hodgepodge coalesce into a single, core metric. (Getting the hodgepodge to coalesce is hard, and the central point of the scientific refinement step I talk about in the Strategy doc.)

I think y... (read more)

2Rubi Hudson
When I say corrigibility as a modifier, I mean it as a transformation that could be applied to a wide range of utility functions. To use an example from the 2015 MIRI paper, you can take most utility functions and add a term that says "if you shut down when the button is pressed, you get utility equal to the expected value of not shutting down". Alternatively, it could be an optimization constraint that takes a utility function from "Maximize X" to something like "Maximize X s.t. you always shut down when the shutdown button is pushed". While I'm not advocating for those specific changes, I hope they illustrate what I'm trying to point at as a modifier that is distinct from the optimization goal.

It sounds like you're proposing a system that is vulnerable to the Fully Updated Deference problem, and where if it has a flaw in how it models your preferences, it can very plausibly go against your words. I don't think that's corrigible.

In the specific example, just because one is confused about what they want doesn't mean the AI will be (or should be). It seems like you think the AGI should not "take a guess" at the preferences of the principal, but it should listen to what the principal says. Where is the qualitative line between the two? In your syste... (read more)

4Seth Herd
This seems productive. I don't understand your proposal if it doesn't boil down to "do what the principal wants" or "do what the principal says" (correctly interpreted and/or carefully verified). This makes me worried that what you have in mind is not that simple and coherent and therefore relatively easy to define or train into an AGI. This (maybe misunderstanding) of your corrigibility=figure out what I want is why I currently prefer the instruction-following route to corrigibility. I don't want the AGI to guess at what I want any more than necessary. This has downsides, too; back to those at the end. I do think what your model of me says, but I think it's only narrowly true and probably not very useful that I think this is true for exactly the right definition of "what I want", but conveying that to an AGI is nontrivial, and re-introduces the difficulty of value learning. That's mixed with the danger that it's incorrect about what I want. That is, it could be right about what I want in one sense, but not the sense I wanted to convey to it (E.G., it decides I'd really rather be put into an experience machine where I'm the celebrated hero of the world, rather than make the real world good for everyone like I'd hoped to get). Maybe I've misunderstood your thesis, but I did read it pretty carefully, so there might be something to learn from how I've misunderstood. All of your examples I remember correspond to "doing what the principal wants" by a pretty common interpetation of that phrase. Instruction-following puts a lot of the difficulty back on the human(s) in charge. This is potentially very bad, but I think humans will probably choose this route anyway. You've pointed out some ways that following instructions could be a danger (although I think your genie examples aren't the most relevant for a modest takeoff speed). But I think unless something changes, humans are likely to prefer keeping the power and the responsibility to trying to put more of the proje

I don't think "a corrigible agent wants to do what the principal wants, at all times" matches my proposal. The issue that we're talking here shows up in the math, above, in that the agent needs to consider the principal's values in the future, but those values are themselves dependent on the agent's action. If the principal gave a previous command to optimize for having a certain set of values in the future, sure, the corrigible agent can follow that command, but to proactively optimize for having a certain set of values doesn't seem necessarily corrigible... (read more)

2Seth Herd
This sounds like we're saying the same thing? My "at all times" is implied and maybe confusing. I'm saying it doesn't guess what the principal will want in the future, it just does what they want now. That probably includes not manipulating their future values. Their commands are particularly strong evidence of what they want, but at core, it's just having the agent's goals be a pointer to the principal's goals. This formulation occurred to me since talking to you, and it seems like a compact and intuitive formulation of why your notion of corrigibility seems coherent and simple. Edit: to address your example, I both want and don't-want to be manipulated into wanting to exercise next week. It's confusing for me, so it should be confusing for my corrigible AGI. It should ask me to clarify when and how I want to be manipulated, rather than taking a guess when I don't know the answer. I probably haven't thought about it deeply, and overall it's pretty important to accurately doing what I want, so a good corrigible helper will suggest I spend some time clarifying for it and for myself. This is a point where things could go wrong if it takes bad guesses instead of getting clarification, but there are lots of those.

Thanks. Picking out those excerpts is very helpful.

I've jotted down my current (confused) thoughts about human values.

But yeah, I basically think one needs to start with a hodgepodge of examples that are selected for being conservative and uncontroversial. I'd collect them by first identifying a robust set of very in-distribution tasks and contexts and try to exhaustively identify what manipulation would look like in that small domain, then aggressively train on passivity outside of that known distribution. The early pseudo-agent will almost certainly be m... (read more)

Thanks! I now feel unconfused. To briefly echo back the key idea which I heard (and also agree with): a technique which can create a corrigible PAAI might have assumptions which break if that technique is used to make a different kind of AI (i.e. one aimed at CEV). If we call this technique "the Corrigibility method" then we may end up using the Corrigibility method to make AIs that aren't at all corrigible, but merely seem corrigible, resulting in disaster.

This is a useful insight! Thanks for clarifying. :)

  • In "What Makes Corrigibility Special", where you use the metaphor of goals as two-dimensional energy landscape, it is not clear what type of goals are being considered.
    • Are these utility functions over world-states? If so, corrigibility cannot AFAIK be easily expressed as one, and so doesn't really fit into the picture.
    • If not, it's not clear to me why most of this space is flat: agents are embedded and many things we do in service of goals will change us in ways that don't conflict with our existing goals, including developing. E.g. if I have the goal of gr
... (read more)

At that point, it is clever enough to convince the designers that this IO is the objectively correct thing to do, using only methods classified as AE.

I'm confused here. Is the corrigible AI trying to get the IO to happen? Why is it trying to do this? Doesn't seem very corrigible, but I think I'm probably just confused.

Maybe another frame on my confusion is that it seems to me that a corrigible AI can't have an IO?

2ThomasCederborg
Thank you for engaging. If this was unclear for you, then I'm sure it was also unclear for others. The post outlined a scenario where a Corrigibility method works perfectly for one type of AI (an AI that does not imply an identifiable outcome, for example a PAAI). The same Corrigibility method fails completely for another type of AI (an AI that does imply an identifiable outcome, for example PCEV). So the second AI, that does have an IO, is indeed not corrigible. This Corrigibility method leads to an outcome that is massively worse than extinction. This bad outcome is the result of two things being true, (i): the fully Corrigible first AI made this outcome possible to reach, and (ii): since the Corrigibility method worked perfectly for the first AI, the designers falsely believed that the Corrigibility method would also work for the second AI. The second AI wants many things. It wants to get an outcome, as close as possible to IO. The Corrigibility method resulted in the second AI also wanting many additional things (such as wanting all explanations it gives to count as AE, even if this makes the explanations less efficient. And wanting to avoid implementing anything, unless informed designers want that thing to be implemented). But in practice the Corrigibility method does not change the outcome in any way (it just adds an ``explanation step''). So I think it makes sense to say that the second AI has ``zero Corrigibility''. The first AI is completely corrigible. And if the designers had only used the Corrigibility method for the first AI, then the Corrigibility method would have worked perfectly. This is what I was trying to communicate with the first sentence of the post:  ``A Corrigibility method that works for a Pivotal Act AI (PAAI) but fails for a CEV style AI could make things worse.''. I could have used that sentence as a title, but I decided against trying to include everything in the title. (I think it is ok to leave information out of the title, as lo

I'd like to get better at communication such that future people I write/talk to don't have a similar feeling of a rug-pull. If you can point to specific passages from earlier documents that you feel set you up for disappointment, I'd be very grateful.

I now think that corrigibility is a single, intuitive property

My intuitive notion of corrigibility can be straightforwardly leveraged to build a formal, mathematical measure.

This formal measure is still lacking, and almost certainly doesn’t actually capture what I mean by “corrigibility.”

I don't know, maybe it's partially or mostly my fault for reading too much optimism into these passages... But I think it would have managed my expectations better to say something like "my notion of corrigibility heavily depends on a subnotion of 'don't manipulat... (read more)

I'm going to respond piece-meal, since I'm currently writing in a limited timebox.

Empowering the principal to fix its flaws and mistakes how? [...]

If the "perfectly corrigible agent" it something that only reflects on itself and tries to empower the principal to fix it, it would be useless at anything else, like curing cancer.

I think obedience is an emergent behavior of corrigibility. The intuitive story here is that how the AI moves its body is a kind of action, and insofar as the principal gives a command, this is an attempt to "fix" the action to be one... (read more)

2Elliott Thornley
In that case, I'm confused about how the process of training an agent to be corrigible differs from the process of training an agent to be fully aligned / DWIM (i.e. training the agent to always do what we want). And that makes me confused about how the proposal addresses problems of reward misspecification, goal misgeneralization, deceptive alignment, and lack of interpretability. You say some things about gradually exposing agents to new tasks and environments (which seems sensible!), but I'm concerned that that by itself won't give us any real assurance of corrigibility.

Yep. sim is additionally bad because it prevents the AI from meaningfully defending against manipulation by others. It's worse than that, even, since the AI can't even let the principal use general tools the AI provides (i.e. a fortress) to defend against being manipulated from outside. In the limit, this might result in the AI manipulating the principals on the behalf of others who would've counterfactually influenced them. I consider the version I've provided to be obviously inadequate, and this is another pointer as to why.

Towards the end of the documen... (read more)

Want to explain a bit about how you'd go about doing this?

I don't think there's a particular trick, here. I can verify a certain amount of wisdom, and have already used that to gain some trust in various people. I'd go to the people I trust and ask them how they'd solve the problem, then try to spot common techniques and look for people who were pointed to independently. I'd attempt to get to know people who were widely seen as trustworthy and understand why they had that reputation and try not to get Goodharted too hard. I'd try to get as much diversity a... (read more)

1) I'm pretty bearish on standard value uncertainty for standard MIRI reasons. I think a correct formulation of corrigibility will say that even if you (the agent) knows what the principal wants, deep in their heart, you should not optimize for it unless they direct you to do so. I explore this formally in 3b, when I talk about the distinction between sampling counterfactual values from the actual belief state over values ("P") vs a simplicity-weighted distribution ("Q"). I do think that value "uncertainty" is important in the sense that it's important for... (read more)

I think that there are small groups of people that can form a sufficiently wise consensus that I would entrust them to govern a corrigible ASI. I don't think I, personally, could do a good job right this moment, not having spent much time specializing in knowing/finding such people. But I also think that if you gave me a year where I had lots of money, access, and was free from people trying to pressure me, I would have a good shot at pulling it off.

I do not trust the world's governments to agree on anything, much less something as contentious as this. It ... (read more)

3Wei Dai
Want to explain a bit about how you'd go about doing this? Seems like you're facing some similar problems as assuring that an AI is wise, benevolent, and stable, e.g., not knowing what wisdom really is, distribution shift between testing and deployment, adversarial examples/inputs. I think this means you should be extra careful not to inadvertently make people too optimistic about alignment, which would make coordination to stop capabilities research even harder than it already is. For example you said that you "like" the visualization of 5 humans selected by various governments, without mentioning that you don't trust governments to do this, which seems like a mistake?

I'm curious for whether your perspective shifts once you read https://www.alignmentforum.org/posts/QzC7kdMQ5bbLoFddz/2-corrigibility-intuition and the formalism documents I'm publishing tomorrow.

I gave a simple definition of corrigibility at the start of the doc:

[A corrigible agent is one] that robustly and cautiously reflects on itself as a flawed tool and focus[es] on empowering the principal to fix its flaws and mistakes

But the big flaw with just giving an English sentence like that is that it's more like a checksum than a mathematic... (read more)

Ah, yeah! That'd be great. Am I capable of doing that, or do you want to handle it for me?

4Oliver Habryka
You can do it. Just go to https://www.lesswrong.com/library and scroll down until you reach the "Community Sequences" section and press the "Create New Sequence" button.