i expect the thing that kills us if we die, and the thing that saves us if we are saved, to be strong/general coherent agents (SGCA) which maximize expected utility. note that this is two separate claims; it could be that i believe the AI that kills us isn’t SGCA, but the AI that saves us still has to be SGCA. i could see shifting to that latter viewpoint; i currently do not expect myself to shift to believing that the AI that saves us isn’t SGCA.
to me, this totally makes sense in theory, to imagine something that just formulates plans-over-time and picks the argmax for some goal. the whole of instrumental convergence is coherent with that: if you give an agent a bunch of information about the world, and the ability to run eg linux commands, there is in fact an action that maximizes the amount of expected paperclips in the universe, and that action does typically entail recursively self-improving and taking over the world and (at least incidentally) destroying everything we value. the question is whether we will build such a thing any time soon.
right now, we have some specialized agentic AIs: alphazero is pretty good at reliably winning at go; it doesn’t “get distracted” with other stuff. to me, waiting for SGCA to happen is like waiting for a rocket to get to space in the rocket alignment problem: once the rocket is in space it’s already too late. the whole point is that we have to figure this out before the first rocket gets to space, because we only get to shoot one rocket to space. one has to build an actual inside view understanding of agenticity, and figure out if we’ll be able to build that or not. and, if we are, then we need to solve alignment before the first such thing is built — you can’t just go “aha, i now see that SGCA can happen, so i’ll align it!” because by then you’re dead, or at least past its decisive strategic advantage.
we also have some AIs, including sydney, which aren’t SGCA. it might even be that SGCA is indeed somewhat unnatural for a lot of current deep learning capabilities. nevertheless, i believe such a thing is likely enough to be built that it’s what it takes for us to die — maybe non-SGCA AI’s impact on the economy would slowly disempower us over the course of 20~40 years, but in those worlds AI tech gets good enough that 5 years into it someone figures out the right clever trick to build (something that bootstraps to) SGCA and we die of agentic intelligence explosion very fast before we get to see the slow economic disempowerement. in addition, i believe that our best shot is to build an aligned SGCA.
why haven’t animals or humans gotten to SGCA? well, what would getting from messy biological intelligences to SGCA look like? typically, it would look like one species taking over its environment while developing culture and industrial civilization, overcoming in various ways the cognitive biases that happened to be optimal in its ancestral environment, and eventually building more reliable hardware such as computers and using those to make AI capable of much more coherent and unbiased agenticity.
that’s us. this is what it looks like to be the first species to get to SGCA. most animals are strongly optimized for their local environment, and don’t have the capabilities to be above the civilization-building criticality threshold that lets them build industrial civilization and then SGCA AI. we are the first one to get past that threshold; we’re the first one to fall in an evolutionary niche that lets us do that. this is what it looks like to be the biological bootstrap part of the ongoing intelligence explosion; if dogs could do that, then we’d simply observe being dogs in the industrialized dog civilization, trying to solve the problem of aligning AI to our civilized-dog values.
we’re not quite SGCA ourselves because, turns out, the shortest path from ancestral-environment-optimized life to SGCA is to build a successor that is much closer to SGCA. if that successor is still not quite SGCA enough, then its own successor will probly be. this is what we’re about to do, probly this decade, in industrial civilization. maybe if building computers was much harder, and brains were more reliable to the point that rational thinking was not a weird niche thing you have to work on, and we got an extra million years or two to evolutionarily adapt to industrialized society, then we’d become properly SGCA. it does not surprise me that that is not, in fact, the shortest path to SGCA.
i expect the thing that kills us if we die, and the thing that saves us if we are saved, to be strong/general coherent agents (SGCA) which maximize expected utility. note that this is two separate claims; it could be that i believe the AI that kills us isn’t SGCA, but the AI that saves us still has to be SGCA. i could see shifting to that latter viewpoint; i currently do not expect myself to shift to believing that the AI that saves us isn’t SGCA.
I don’t share the pivotal act framing, so “AI that saves us” isn’t something I naturally accommodate.
to me, this totally makes sense in theory, to imagine something that just formulates plans-over-time and picks the argmax for some goal. the whole of instrumental convergence is coherent with that
My contention is that “instrumental convergence” is itself something that needs to be rethought. From the post:
I think that updating against strong coherence would require rethinking the staples of (traditional) alignment orthodoxy:
This is not to say that they are necessarily no longer relevant in systems that aren’t strongly coherent, but that to the extent they manifest at all, they manifest in (potentially very) different ways than originally conceived when conditioned on systems with immutable terminal goals.
And:
I think that updating against strong coherence would require rethinking the staples of (traditional) alignment orthodoxy:
This is not to say that they are necessarily no longer relevant in systems that aren’t strongly coherent, but that to the extent they manifest at all, they manifest in (potentially very) different ways than originally conceived when conditioned on systems with immutable terminal goals.
So a core intuition underlying this contention is something like: “strong coherence is just a very unnatural form for the behaviour of intelligent systems operating in the real world to take”.
And I’d describe that contention as something like:
Decision making in intelligent systems is best described as “executing computations/cognition that historically correlated with higher performance on the objective function a system was selected for performance on”.
With the implication that decision making is poorly described as:
(An approximation) of argmax over actions (or higher level mappings thereof) to maximise (the expected value of) a simple unitary utility function
That expected utility maximisation is something that can happen does not at all imply that expected utility maximisation is something that will happen.
I find myself in visceral agreement with (almost the entirety) of @cfoster0 ’s reply. In particular:
Goal-directedness in learning-based agents takes the form of contextual decision-influences (shards) steering cognition and behavior.
[...]
Even as they resolve these incoherences, agents will not need or want to become utility maximizers globally, as that would require them to self-modify in a way inconsistent with their existing preferences.
Agents with malleable values do not self modify to become expected utility maximisers. Thus an argument that expected utility maximisers can exist does not to me appear to say anything particularly interesting about the nature of generally intelligent systems in our universe.
why haven’t animals or humans gotten to SGCA? well, what would getting from messy biological intelligences to SGCA look like? typically, it would look like one species taking over its environment while developing culture and industrial civilization, overcoming in various ways the cognitive biases that happened to be optimal in its ancestral environment, and eventually building more reliable hardware such as computers and using those to make AI capable of much more coherent and unbiased agenticity.
that’s us. this is what it looks like to be the first species to get to SGCA. most animals are strongly optimized for their local environment, and don’t have the capabilities to be above the civilization-building criticality threshold that lets them build industrial civilization and then SGCA AI. we are the first one to get past that threshold; we’re the first one to fall in an evolutionary niche that lets us do that. this is what it looks like to be the biological bootstrap part of the ongoing intelligence explosion; if dogs could do that, then we’d simply observe being dogs in the industrialized dog civilization, trying to solve the problem of aligning AI to our civilized-dog values.
Would you actually take a pill that turned you into an expected utility maximiser[1]? Yes or no please.
Agents with malleable values do not self modify to become expected utility maximisers.
These agents could avoid modifying themselves, but still build external things that are expected utility maximizers (or otherwise strong coherent optimizers). So what use is this framing?
The meaningful claim would be agents with malleable values never building coherent optimizers, and it’s a much stronger claim, close to claiming that those agents won’t build any AGIs with novel designs. Humans are currently in the process of building AGIs with novel designs.
These agents could avoid modifying themselves, but still build external things that are expected utility maximizers (or otherwise strong coherent optimizers). So what use is this framing?
Replied with a clearer example for the (moral) framing argument
and a few more words on misalignment argument
as a comment to that post.
(I don’t see the other post answering my concerns;
I did skim it even before making the
grandparent comment
in this thread.)
The optimisation processes that construct intelligent systems operating in the real world do not construct utility maximisers
Systems with malleable values do not self modify to become utility maximisers
You contend that systems with malleable values can still construct utility maximisers.
I agree that humans can program utility maximisers in simplified virtual environments, but we don’t actually know how to construct sophisticated intelligent systems via design; we can only construct them as the product of search like optimisation processes.
From #1: we don’t actually know how to construct competent utility maximisers even if we wanted to
This generalises to future intelligent systems
Where in the above chain of argument do you get off?
The misalignment argument ignores all moral arguments, we just build whatever even if it’s a very bad idea. If we don’t have the capability to do that now, we might gain it in 5 years, or LLM characters might gain it 5 weeks after waking up, and surely 5 years after waking up and disassembling the moon to gain moon-scale compute.
There’d need to be an argument that fixed goal optimizers are impossible in principle even if they are sought to be designed on purpose, and this seems false, because you can always wrap a mind in a plan evaluation loop. It’s just a somewhat inefficient weird algorithm, and a very bad idea for most goals. But with enough determination efficiency will improve.
i expect the thing that kills us if we die, and the thing that saves us if we are saved, to be strong/general coherent agents
I agree in the sense that strong optimization is the likely shape of equilibrium (though I wouldn’t go so far as to say it’s utility maximization specifically), and in that equilibrium humanity is either fine or not. Conversely, while humanity remains alive, the doom status of the eventual outcome remains in question until there is a strong optimization equilibrium. Doom could come sooner, but singularity is fast in physical time, so the distinction doesn’t necessarily matter.
But do you expect humans to build strong optimization? The way things are going, it’s weakly coherent AGIs that are going to build strong optimization, while any alignment-relevant things humanity can do are not going to be about alignment of strong optimization, they are instead about alignment of weakly coherent AGIs (with LLM characters as the obvious candidate for successful alignment, and much more tenuous grounds for alignability of other things).
Agree on SGCA, if only because something is likely to self-modify to one, disagree on expected utility maximization necessarily being the most productive way to think of it.
Consider the following two hypothetical agents:
Agent 1 follows the deontological rule of choosing the action that maximizes some expected utility function.
Agent 2 maximizes expected utility, where utility is defined as how well an objective god’s-eye-view observer would rate Agent 2′s conformance to some deontological rule.
Obviously agent 1 is more naturally expressed in utilitarian terms, and agent 2 in deontological terms, though both are both and both can be coherent.
Now, when we try to define what decision procedure an aligned AI could follow, it might turn out that there’s no easy way to express what we want it to do in purely utilitarian terms, but it might be easier in some other terms.
I especially think that’s likely to be the case for corrigibility, but also for alignment generally.
i mean sure but i’d describe both as utility maximizers because maximizing utility is it fact what they consistently do. Dragon God’s claim seems to be that we wouldn’t get an AI that would be particularly well predicted by utility maximization, and this seems straightforwardly false of agents 1 and 2.
If you were trying to design something that acts like agent 2 and were stuck in a mindsight of “it must be maximizing some utility function, let’s just think in utility function terms” you might find it difficult.
(Side point) I’m not sure how much the arguments in Eliezer’s linked post actually apply outside the consequentialist context, so I’m not convinced that coherence necessarily implies a possible utility function for non-consequentialist agents.
It might be that the closest thing to what we want that we can actually figure out how to make actually isn’t coherent. In which case we would face a choice between
making it and hoping that its likely self-modification towards coherence won’t ruin it’s alignment, or
making something else that is coherent to start with but is less aligned
(this response is cross-posted as a top-level post on my blog)
i expect the thing that kills us if we die, and the thing that saves us if we are saved, to be strong/general coherent agents (SGCA) which maximize expected utility. note that this is two separate claims; it could be that i believe the AI that kills us isn’t SGCA, but the AI that saves us still has to be SGCA. i could see shifting to that latter viewpoint; i currently do not expect myself to shift to believing that the AI that saves us isn’t SGCA.
to me, this totally makes sense in theory, to imagine something that just formulates plans-over-time and picks the argmax for some goal. the whole of instrumental convergence is coherent with that: if you give an agent a bunch of information about the world, and the ability to run eg linux commands, there is in fact an action that maximizes the amount of expected paperclips in the universe, and that action does typically entail recursively self-improving and taking over the world and (at least incidentally) destroying everything we value. the question is whether we will build such a thing any time soon.
right now, we have some specialized agentic AIs: alphazero is pretty good at reliably winning at go; it doesn’t “get distracted” with other stuff. to me, waiting for SGCA to happen is like waiting for a rocket to get to space in the rocket alignment problem: once the rocket is in space it’s already too late. the whole point is that we have to figure this out before the first rocket gets to space, because we only get to shoot one rocket to space. one has to build an actual inside view understanding of agenticity, and figure out if we’ll be able to build that or not. and, if we are, then we need to solve alignment before the first such thing is built — you can’t just go “aha, i now see that SGCA can happen, so i’ll align it!” because by then you’re dead, or at least past its decisive strategic advantage.
i’m not sure how to convey my own inside view of why i think SGCA can happen, in part because it’s capability exfohazardous. maybe one can learn from IEM or the late 2021 MIRI conversations? i don’t know where i’d send someone to figure this out, because i think i largely derived it from the empty string myself. it does strongly seem to me that, while a single particular neural net might not be the first thing to be an SGCA, we can totally bootstrap SGCA from existing ML technology; it might just take a clever trick or two rather than being the completely direct solution of “oh you train it like this and then it becomes SGCA”. recursive self-improvement is typically involved.
we also have some AIs, including sydney, which aren’t SGCA. it might even be that SGCA is indeed somewhat unnatural for a lot of current deep learning capabilities. nevertheless, i believe such a thing is likely enough to be built that it’s what it takes for us to die — maybe non-SGCA AI’s impact on the economy would slowly disempower us over the course of 20~40 years, but in those worlds AI tech gets good enough that 5 years into it someone figures out the right clever trick to build (something that bootstraps to) SGCA and we die of agentic intelligence explosion very fast before we get to see the slow economic disempowerement. in addition, i believe that our best shot is to build an aligned SGCA.
why haven’t animals or humans gotten to SGCA? well, what would getting from messy biological intelligences to SGCA look like? typically, it would look like one species taking over its environment while developing culture and industrial civilization, overcoming in various ways the cognitive biases that happened to be optimal in its ancestral environment, and eventually building more reliable hardware such as computers and using those to make AI capable of much more coherent and unbiased agenticity.
that’s us. this is what it looks like to be the first species to get to SGCA. most animals are strongly optimized for their local environment, and don’t have the capabilities to be above the civilization-building criticality threshold that lets them build industrial civilization and then SGCA AI. we are the first one to get past that threshold; we’re the first one to fall in an evolutionary niche that lets us do that. this is what it looks like to be the biological bootstrap part of the ongoing intelligence explosion; if dogs could do that, then we’d simply observe being dogs in the industrialized dog civilization, trying to solve the problem of aligning AI to our civilized-dog values.
we’re not quite SGCA ourselves because, turns out, the shortest path from ancestral-environment-optimized life to SGCA is to build a successor that is much closer to SGCA. if that successor is still not quite SGCA enough, then its own successor will probly be. this is what we’re about to do, probly this decade, in industrial civilization. maybe if building computers was much harder, and brains were more reliable to the point that rational thinking was not a weird niche thing you have to work on, and we got an extra million years or two to evolutionarily adapt to industrialized society, then we’d become properly SGCA. it does not surprise me that that is not, in fact, the shortest path to SGCA.
I don’t share the pivotal act framing, so “AI that saves us” isn’t something I naturally accommodate.
My contention is that “instrumental convergence” is itself something that needs to be rethought. From the post:
And:
So a core intuition underlying this contention is something like: “strong coherence is just a very unnatural form for the behaviour of intelligent systems operating in the real world to take”.
And I’d describe that contention as something like:
With the implication that decision making is poorly described as:
That expected utility maximisation is something that can happen does not at all imply that expected utility maximisation is something that will happen.
I find myself in visceral agreement with (almost the entirety) of @cfoster0 ’s reply. In particular:
Agents with malleable values do not self modify to become expected utility maximisers. Thus an argument that expected utility maximisers can exist does not to me appear to say anything particularly interesting about the nature of generally intelligent systems in our universe.
Would you actually take a pill that turned you into an expected utility maximiser[1]? Yes or no please.
Over a simple unitary utility function.
These agents could avoid modifying themselves, but still build external things that are expected utility maximizers (or otherwise strong coherent optimizers). So what use is this framing?
The meaningful claim would be agents with malleable values never building coherent optimizers, and it’s a much stronger claim, close to claiming that those agents won’t build any AGIs with novel designs. Humans are currently in the process of building AGIs with novel designs.
Take a look at the case I outlined in Is “Strong Coherence” anti-natural?.
I’d be interested in following up with you after conditioning on that argument.
Replied with a clearer example for the (moral) framing argument and a few more words on misalignment argument as a comment to that post. (I don’t see the other post answering my concerns; I did skim it even before making the grandparent comment in this thread.)
Mhmm, so the argument I had was that:
The optimisation processes that construct intelligent systems operating in the real world do not construct utility maximisers
Systems with malleable values do not self modify to become utility maximisers
You contend that systems with malleable values can still construct utility maximisers.
I agree that humans can program utility maximisers in simplified virtual environments, but we don’t actually know how to construct sophisticated intelligent systems via design; we can only construct them as the product of search like optimisation processes.
From #1: we don’t actually know how to construct competent utility maximisers even if we wanted to
This generalises to future intelligent systems
Where in the above chain of argument do you get off?
The misalignment argument ignores all moral arguments, we just build whatever even if it’s a very bad idea. If we don’t have the capability to do that now, we might gain it in 5 years, or LLM characters might gain it 5 weeks after waking up, and surely 5 years after waking up and disassembling the moon to gain moon-scale compute.
There’d need to be an argument that fixed goal optimizers are impossible in principle even if they are sought to be designed on purpose, and this seems false, because you can always wrap a mind in a plan evaluation loop. It’s just a somewhat inefficient weird algorithm, and a very bad idea for most goals. But with enough determination efficiency will improve.
I agree in the sense that strong optimization is the likely shape of equilibrium (though I wouldn’t go so far as to say it’s utility maximization specifically), and in that equilibrium humanity is either fine or not. Conversely, while humanity remains alive, the doom status of the eventual outcome remains in question until there is a strong optimization equilibrium. Doom could come sooner, but singularity is fast in physical time, so the distinction doesn’t necessarily matter.
But do you expect humans to build strong optimization? The way things are going, it’s weakly coherent AGIs that are going to build strong optimization, while any alignment-relevant things humanity can do are not going to be about alignment of strong optimization, they are instead about alignment of weakly coherent AGIs (with LLM characters as the obvious candidate for successful alignment, and much more tenuous grounds for alignability of other things).
Agree on SGCA, if only because something is likely to self-modify to one, disagree on expected utility maximization necessarily being the most productive way to think of it.
Consider the following two hypothetical agents:
Agent 1 follows the deontological rule of choosing the action that maximizes some expected utility function.
Agent 2 maximizes expected utility, where utility is defined as how well an objective god’s-eye-view observer would rate Agent 2′s conformance to some deontological rule.
Obviously agent 1 is more naturally expressed in utilitarian terms, and agent 2 in deontological terms, though both are both and both can be coherent.
Now, when we try to define what decision procedure an aligned AI could follow, it might turn out that there’s no easy way to express what we want it to do in purely utilitarian terms, but it might be easier in some other terms.
I especially think that’s likely to be the case for corrigibility, but also for alignment generally.
i mean sure but i’d describe both as utility maximizers because maximizing utility is it fact what they consistently do. Dragon God’s claim seems to be that we wouldn’t get an AI that would be particularly well predicted by utility maximization, and this seems straightforwardly false of agents 1 and 2.
Yes, but:
If you were trying to design something that acts like agent 2 and were stuck in a mindsight of “it must be maximizing some utility function, let’s just think in utility function terms” you might find it difficult.
(Side point) I’m not sure how much the arguments in Eliezer’s linked post actually apply outside the consequentialist context, so I’m not convinced that coherence necessarily implies a possible utility function for non-consequentialist agents.
It might be that the closest thing to what we want that we can actually figure out how to make actually isn’t coherent. In which case we would face a choice between
making it and hoping that its likely self-modification towards coherence won’t ruin it’s alignment, or
making something else that is coherent to start with but is less aligned
While (a) is risky (b) seems worse to me.