My concern is similar to Wei Dai’s: it seems to me that at a fundamental physical level, any plan involving turning on a computer that does important stuff will make pretty big changes to the world’s trajectory in phase space. Heat dissipation will cause atmospheric particles to change their location and momentum, future weather patterns will be different, people will do things at different times (e.g. because they’re waiting for a computer program to run, or because the computer is designed to change the flow of traffic through a city), meet different people, and have different children. As a result, it seems hard for me to understand how impact measures could work in the real world without a choice of representation very close to the representation humans use to determine the value of different worlds. I suspect that this will need input from humans similar to what value learning approaches might need, and that once it’s done one could just do value learning and dispense with the need for impact measures. That being said, this is more of an impression than a belief—I can’t quite convince myself that no good method of impact regularisation exists, and some other competent people seem to disagree with me.
I don’t see how representation invariance addresses this concern. As far as I understand, the concern is about any actions in the real world causing large butterfly effects. This includes effects that would be captured by any reasonable representation, e.g. different people existing in the action and inaction branches of the world. The state representations used by humans also distinguish between these world branches, but humans have limited models of the future that don’t capture butterfly effects (e.g. person X can distinguish between the world state where person Y exists and the world state where person Z exists, but can’t predict that choosing a different route to work will cause person Z to exist instead of person Y).
I agree with Daniel that this is a major problem with impact measures. I think that to get around this problem we would either need to figure out how to distinguish butterfly effects from other effects (and then include all the butterfly effects in the inaction branch) or use a weak world model that does not capture butterfly effects (similarly to humans) for measuring impact. Even if we know how to do this, it’s not entirely clear whether we should avoid penalizing butterfly effects. Unlike humans, AI systems would be able to cause butterfly effects on purpose, and could channel their impact through butterfly effects if they are not penalized.
I don’t see how representation invariance addresses this concern.
I think my post was basically saying “representation selection seems like a problem because people are confused about the type signature of impact, which is actually a thing you can figure out no matter what you think the world is made of”. I don’t want to go into too much detail here (as I explained below), but part of what this implies is that discrete “effects” are fake/fuzzy mental constructs/not something to think about when designing an impact measure. In turn, this would mean we should ask a different question that isn’t about butterfly effects.
Unlike humans, AI systems would be able to cause butterfly effects on purpose, and could channel their impact through butterfly effects if they are not penalized.
Indeed—a point I think is illustrated by the Chaotic Hurricanes test case. I’m probably most excited about methods that would use transparency techniques to determine when a system is deliberately optimising for a part of the world (e.g. the members of the long-term future population) that we don’t want it to care about, but this has a major drawback of perhaps requiring multiple philosophical advances into the meaning of reference in cognition and a greater understanding of what optimisation is.
What would you predict AUP does for the chaotic scenarios? Suppose the attainable set just includes the survival utility function, which is 1 if the agent is activated and 0 otherwise.
I think that under the worldview of this concern, the distribution of reward functions effectively defines a representation that, if too different from the one humans care about, will either mean that no realistic impact is possible in the real world or be ineffective at penalising unwanted negative impacts.
My concern is similar to Wei Dai’s: it seems to me that at a fundamental physical level, any plan involving turning on a computer that does important stuff will make pretty big changes to the world’s trajectory in phase space. Heat dissipation will cause atmospheric particles to change their location and momentum, future weather patterns will be different, people will do things at different times (e.g. because they’re waiting for a computer program to run, or because the computer is designed to change the flow of traffic through a city), meet different people, and have different children. As a result, it seems hard for me to understand how impact measures could work in the real world without a choice of representation very close to the representation humans use to determine the value of different worlds. I suspect that this will need input from humans similar to what value learning approaches might need, and that once it’s done one could just do value learning and dispense with the need for impact measures. That being said, this is more of an impression than a belief—I can’t quite convince myself that no good method of impact regularisation exists, and some other competent people seem to disagree with me.
How does this concern interact with the effective representation invariance claim I made when introducing AUP?
I don’t see how representation invariance addresses this concern. As far as I understand, the concern is about any actions in the real world causing large butterfly effects. This includes effects that would be captured by any reasonable representation, e.g. different people existing in the action and inaction branches of the world. The state representations used by humans also distinguish between these world branches, but humans have limited models of the future that don’t capture butterfly effects (e.g. person X can distinguish between the world state where person Y exists and the world state where person Z exists, but can’t predict that choosing a different route to work will cause person Z to exist instead of person Y).
I agree with Daniel that this is a major problem with impact measures. I think that to get around this problem we would either need to figure out how to distinguish butterfly effects from other effects (and then include all the butterfly effects in the inaction branch) or use a weak world model that does not capture butterfly effects (similarly to humans) for measuring impact. Even if we know how to do this, it’s not entirely clear whether we should avoid penalizing butterfly effects. Unlike humans, AI systems would be able to cause butterfly effects on purpose, and could channel their impact through butterfly effects if they are not penalized.
I think my post was basically saying “representation selection seems like a problem because people are confused about the type signature of impact, which is actually a thing you can figure out no matter what you think the world is made of”. I don’t want to go into too much detail here (as I explained below), but part of what this implies is that discrete “effects” are fake/fuzzy mental constructs/not something to think about when designing an impact measure. In turn, this would mean we should ask a different question that isn’t about butterfly effects.
Indeed—a point I think is illustrated by the Chaotic Hurricanes test case. I’m probably most excited about methods that would use transparency techniques to determine when a system is deliberately optimising for a part of the world (e.g. the members of the long-term future population) that we don’t want it to care about, but this has a major drawback of perhaps requiring multiple philosophical advances into the meaning of reference in cognition and a greater understanding of what optimisation is.
What would you predict AUP does for the chaotic scenarios? Suppose the attainable set just includes the survival utility function, which is 1 if the agent is activated and 0 otherwise.
I think that under the worldview of this concern, the distribution of reward functions effectively defines a representation that, if too different from the one humans care about, will either mean that no realistic impact is possible in the real world or be ineffective at penalising unwanted negative impacts.
is there a central example you have in mind for this potential failure mode?
No.
No good method of measuring impact, presumably?
I prefer the phrase ‘impact regularisation’, but indeed that was a slip of the mind.