That being said, my model of Yudkowsky, which I built by spending time interpreting and reverse engineering the post you’re responding to, feels like you’re not addressing his points (obviously, I might have missed the real Yudkowsky’s point)
My interpretation is that he is saying that Evolution (as the generator of most biological anchors) explores the solution space in a fundamentally different path than human research. So what you have is two paths through a space. The burden of proof for biological anchors thus lies in arguing that there are enough connections/correlations between the two paths to use one in order to predict the other.
Here it sounds like you’re taking as an assumption that human research follows the same or a faster path towards the same point in search space. But that’s actually the assumption that IMO Yudkowsky is criticizing!
In his piece, Yudkowsky is giving arguments that the human research path should lead to more efficient AGIs than evolution, in part due to the ability of humans to have and leverage insights, which the naive optimization process of evolution can’t do. He also points to the inefficiency of biology in implementing new (in geological-time) complex solutions. On the other hand, he doesn’t seem to see a way of linking the amount of resources needed by evolution to the amount of resources needed by human research, because they are so different.
If the two paths are very different and don’t even aim at the same parts of the search space, there’s nothing telling you that computing the optimization power of the first path helps in understanding the second one.
I think Yudkowsky would agree that if you could estimate the amount of resources needed to simulate all evolution until humans at the level of details that you know is enough to capture all relevant aspects, that amount of resources would be an upper bound on the time taken by human research because that’s a way to get AGI if you have the resources. But the number is so vastly large (and actually unknown due to the “level of details” problem) that it’s not really relevant for timelines calculations
(Also, I already had this discussion with Daniel Kokotajlo in this thread, but I really think that Platt’s law is one of the least cruxy aspects of the original post. So I don’t think discussing it further or pointing attention to it is a good idea)
It displeases me that this is currently the most upvoted response: I believe you are focusing on EY’s weakest rather than strongest points.
My interpretation is that he is saying that Evolution (as the generator of most biological anchors) explores the solution space in a fundamentally different path than human research. So what you have is two paths through a space. The burden of proof for biological anchors thus lies in arguing that there are enough connections/correlations between the two paths to use one in order to predict the other.
It’s hardly surprising there are ‘two paths through a space’ - if you reran either (biological or cultural/technological) evolution with slightly different initial conditions you’d get a different path. However technological evolution is aware of biological evolution and thus strongly correlated to and influenced by it. IE deep learning is in part brain reverse engineering (explicitly in the case of DeepMind, but there are many other examples). The burden proof is thus arguably more opposite of what you claim (EY claims).
In his piece, Yudkowsky is giving arguments that the human research path should lead to more efficient AGIs than evolution, in part due to the ability of humans to have and leverage insights, which the naive optimization process of evolution can’t do. He also points to the inefficiency of biology in implementing new (in geological-time) complex solutions.
To the extent EY makes specific testable claims about the inefficiency of biology, those claims are in err—or at least easily contestable.
EY’ strongest point is that the Bio Anchors framework puts far too much weight on scaling of existing models (ie transformers) to AGI, rather than modeling improvement in asymptotic scaling itself. GPT-3 and similar model scaling is so obviously inferior to what is probably possible today—let alone what is possible in the near future—that it should be given very little consideration/weight, just as it would be unwise to model AGI based on scaling up 2005 DL tech.
I feel like you’re using “strongest” and “weakest” to design “more concrete” and “more abstract”, with maybe the value judgement (implicit in your focus on specific testable claims) that concreteness is better. My interpretation doesn’t disagree with your point about Bio Anchors, it simply says that this is a concrete instantiation of a general pattern, and that the whole point of the original post as I understand it is to share this pattern. Hence the title who talks about all biology-inspired timelines, the three examples in the post, and the seven times that Yudkowsky repeats his abstract arguments in differents ways.
It’s hardly surprising there are ‘two paths through a space’ - if you reran either (biological or cultural/technological) evolution with slightly different initial conditions you’d get a different path. However technological evolution is aware of biological evolution and thus strongly correlated to and influenced by it. IE deep learning is in part brain reverse engineering (explicitly in the case of DeepMind, but there are many other examples). The burden proof is thus arguably more opposite of what you claim (EY claims).
Maybe a better way of framing my point here is that the optimization processes are fundamentally different (something about which Yudkowsky has written a lot, see for example this post from 13 years ago), and that the burden of proof is on showing that they have enough similarity to extract a lot of info from the evolutionary optimization to the human research optimization.
I also don’t think your point about DeepMind works, because DM is working in a way extremely different from evolution. They are in part reverse engineering the brain, but that’s a very different (and very human and insight heavy) paths towards AGI than the one evolution took.
Lastly for this point, I don’t think the interpretation that “Yudkowsky says that the burden of proof is on showing that the optimization of evolution and human research are non correlated” survives the contact with a text where Yudkowsky constantly berates his interlocutors for assuming such correlation, and keeps drawing again and again the differences.
To the extent EY makes specific testable claims about the inefficiency of biology, those claims are in err—or at least easily contestable.
Hum, I find myself feeling like this comment: Yudkowsky’s main point about biology IMO is that brains are not at all the most efficient computational way of implementing AGI. Another way of phrasing it is that Yudkowsky says (according to me) that you could use significantly less hardware and ops/sec to make an AGI.
To be clear, my disagreement concerns more your implicit prioritization—rather than interpretation—of EY’s points.
I also don’t think your point about DeepMind works, because DM is working in a way extremely different from evolution. They are in part reverse engineering the brain, but that’s a very different (and very human and insight heavy) paths towards AGI than the one evolution took.
If search process Y fully reverse engineers the result of search process X, then Y ends up at the same endpoint as X, regardless of the path Y took. Obviously the path is different but also correlated; and reverse engineering the brain makes brain efficiency considerations (and thus some form of bio anchor) relevant.
Yudkowsky’s main point about biology IMO is that brains are not at all the most efficient computational way of implementing AGI. Another way of phrasing it is that Yudkowsky says (according to me) that you could use significantly less hardware and ops/sec to make an AGI.
Sure, but that’s also the worst part of his argument, because to support it he makes a very specific testable claim concerning thermodynamic efficiency; a claim that is almost certainly off base.
To the extent EY makes specific testable claims about the inefficiency of biology, those claims are in err—or at least easily contestable.
Hum, I find myself feeling like this comment: Yudkowsky’s main point about biology IMO is that brains are not at all the most efficient computational way of implementing AGI. Another way of phrasing it is that Yudkowsky says (according to me) that you could use significantly less hardware and ops/sec to make an AGI.
That’s unfortunate that you agree; here’s the full comment:
You’re missing the point!
Your arguments apply mostly toward arguing that brains are optimized for energy efficiency, but the important quantity in question is computational efficiency! You even admit that neurons are “optimizing hard for energy efficiency at the expense of speed”, but don’t seem to have noticed that this fact makes almost everything else you said completely irrelevant!
Adele claims that I’m ‘missing the point’ by focusing on energy efficiency, but the specific EY claim I disagreed with is very specifically about energy efficiency! Which is highly relevant, because he then uses this claim as evidence to suggest general inefficiency.
EY specifically said the following, repeating the claim twice in slightly different form:
The result is that the brain’s computation is something like half a million times less efficient than the thermodynamic limit for its temperature—so around two millionths as efficient as ATP synthase.
The software for a human brain is not going to be 100% efficient compared to the theoretical maximum, nor 10% efficient, nor 1% efficient, even before taking into account
. . .
That is simply not a kind of thing that I expect Reality to say “Gotcha” to me about, any more than I expect to be told that the human brain, whose neurons and synapses are 500,000 times further away from the thermodynamic efficiency wall than ATP synthase, is the most efficient possible consumer of computation
Adele’s comment completely ignores the very specific point I was commenting on, and strawman’s my position while steelmanning EY’s.
I don’t think I am following the argument here. You seem focused on the comparison with evolution, which is only a minor part of Bio Anchors, and used primarily as an upper bound. (You say “the number is so vastly large (and actually unknown due to the ‘level of details’ problem) that it’s not really relevant for timelines calculations,” but actually Bio Anchors still estimates that the evolution anchor implies a ~50% chance of transformative AI this century.)
Generally, I don’t see “A and B are very different” as a knockdown counterargument to “If A required ___ amount of compute, my guess is that B will require no more.” I’m not sure I have more to say on this point that hasn’t already been said—I acknowledge that the comparisons being made are not “tight” and that there’s a lot of guesswork, and the Bio Anchors argument doesn’t go through without some shared premises and intuitions, but I think the needed intuitions are reasonable and an update from Bio-Anchors-ignorant starting positions is warranted.
Unfortunately, I don’t have the time at the moment to answer in detail and have more of a conversation, as I’m fully focused on writing a long sequence about pushing for pluralism in alignment and extracting the core problem out of all the implementation details and additional assumption. I plan on going back to analyzing timeline research in the future, and will probably give better answers then.
That being said, here are quick fire thoughts:
I used the evolution case because I consider it the most obvious/straightforward case, in that it sounds so large that everyone instantly assumes that it gives you an upper bound.
My general impression about this report (and one I expect Yudkowsky to share) is that it didn’t made me update at all. I already updated from GPT and GPT3, and I didn’t find new bits of evidence in the report and the discussions around it, despite the length of it. My current impression (please bear in mind that I haven’t taken the time to study the report from that angle, so I might change my stance) is that this report, much like a lot of timeline work, seems like it takes as input a lot of assumption, and gives as output far less than was assumed. It’s the opposite of compression — a lot of assumptions are needed to conclude things that aren’t that strong and constraining.
Thanks for this post!
That being said, my model of Yudkowsky, which I built by spending time interpreting and reverse engineering the post you’re responding to, feels like you’re not addressing his points (obviously, I might have missed the real Yudkowsky’s point)
My interpretation is that he is saying that Evolution (as the generator of most biological anchors) explores the solution space in a fundamentally different path than human research. So what you have is two paths through a space. The burden of proof for biological anchors thus lies in arguing that there are enough connections/correlations between the two paths to use one in order to predict the other.
Here it sounds like you’re taking as an assumption that human research follows the same or a faster path towards the same point in search space. But that’s actually the assumption that IMO Yudkowsky is criticizing!
In his piece, Yudkowsky is giving arguments that the human research path should lead to more efficient AGIs than evolution, in part due to the ability of humans to have and leverage insights, which the naive optimization process of evolution can’t do. He also points to the inefficiency of biology in implementing new (in geological-time) complex solutions. On the other hand, he doesn’t seem to see a way of linking the amount of resources needed by evolution to the amount of resources needed by human research, because they are so different.
If the two paths are very different and don’t even aim at the same parts of the search space, there’s nothing telling you that computing the optimization power of the first path helps in understanding the second one.
I think Yudkowsky would agree that if you could estimate the amount of resources needed to simulate all evolution until humans at the level of details that you know is enough to capture all relevant aspects, that amount of resources would be an upper bound on the time taken by human research because that’s a way to get AGI if you have the resources. But the number is so vastly large (and actually unknown due to the “level of details” problem) that it’s not really relevant for timelines calculations
(Also, I already had this discussion with Daniel Kokotajlo in this thread, but I really think that Platt’s law is one of the least cruxy aspects of the original post. So I don’t think discussing it further or pointing attention to it is a good idea)
It displeases me that this is currently the most upvoted response: I believe you are focusing on EY’s weakest rather than strongest points.
It’s hardly surprising there are ‘two paths through a space’ - if you reran either (biological or cultural/technological) evolution with slightly different initial conditions you’d get a different path. However technological evolution is aware of biological evolution and thus strongly correlated to and influenced by it. IE deep learning is in part brain reverse engineering (explicitly in the case of DeepMind, but there are many other examples). The burden proof is thus arguably more opposite of what you claim (EY claims).
To the extent EY makes specific testable claims about the inefficiency of biology, those claims are in err—or at least easily contestable.
EY’ strongest point is that the Bio Anchors framework puts far too much weight on scaling of existing models (ie transformers) to AGI, rather than modeling improvement in asymptotic scaling itself. GPT-3 and similar model scaling is so obviously inferior to what is probably possible today—let alone what is possible in the near future—that it should be given very little consideration/weight, just as it would be unwise to model AGI based on scaling up 2005 DL tech.
Thanks for pushing back on my interpretation.
I feel like you’re using “strongest” and “weakest” to design “more concrete” and “more abstract”, with maybe the value judgement (implicit in your focus on specific testable claims) that concreteness is better. My interpretation doesn’t disagree with your point about Bio Anchors, it simply says that this is a concrete instantiation of a general pattern, and that the whole point of the original post as I understand it is to share this pattern. Hence the title who talks about all biology-inspired timelines, the three examples in the post, and the seven times that Yudkowsky repeats his abstract arguments in differents ways.
Maybe a better way of framing my point here is that the optimization processes are fundamentally different (something about which Yudkowsky has written a lot, see for example this post from 13 years ago), and that the burden of proof is on showing that they have enough similarity to extract a lot of info from the evolutionary optimization to the human research optimization.
I also don’t think your point about DeepMind works, because DM is working in a way extremely different from evolution. They are in part reverse engineering the brain, but that’s a very different (and very human and insight heavy) paths towards AGI than the one evolution took.
Lastly for this point, I don’t think the interpretation that “Yudkowsky says that the burden of proof is on showing that the optimization of evolution and human research are non correlated” survives the contact with a text where Yudkowsky constantly berates his interlocutors for assuming such correlation, and keeps drawing again and again the differences.
Hum, I find myself feeling like this comment: Yudkowsky’s main point about biology IMO is that brains are not at all the most efficient computational way of implementing AGI. Another way of phrasing it is that Yudkowsky says (according to me) that you could use significantly less hardware and ops/sec to make an AGI.
To be clear, my disagreement concerns more your implicit prioritization—rather than interpretation—of EY’s points.
If search process Y fully reverse engineers the result of search process X, then Y ends up at the same endpoint as X, regardless of the path Y took. Obviously the path is different but also correlated; and reverse engineering the brain makes brain efficiency considerations (and thus some form of bio anchor) relevant.
Sure, but that’s also the worst part of his argument, because to support it he makes a very specific testable claim concerning thermodynamic efficiency; a claim that is almost certainly off base.
That’s unfortunate that you agree; here’s the full comment:
Adele claims that I’m ‘missing the point’ by focusing on energy efficiency, but the specific EY claim I disagreed with is very specifically about energy efficiency! Which is highly relevant, because he then uses this claim as evidence to suggest general inefficiency.
EY specifically said the following, repeating the claim twice in slightly different form:
Adele’s comment completely ignores the very specific point I was commenting on, and strawman’s my position while steelmanning EY’s.
I don’t think I am following the argument here. You seem focused on the comparison with evolution, which is only a minor part of Bio Anchors, and used primarily as an upper bound. (You say “the number is so vastly large (and actually unknown due to the ‘level of details’ problem) that it’s not really relevant for timelines calculations,” but actually Bio Anchors still estimates that the evolution anchor implies a ~50% chance of transformative AI this century.)
Generally, I don’t see “A and B are very different” as a knockdown counterargument to “If A required ___ amount of compute, my guess is that B will require no more.” I’m not sure I have more to say on this point that hasn’t already been said—I acknowledge that the comparisons being made are not “tight” and that there’s a lot of guesswork, and the Bio Anchors argument doesn’t go through without some shared premises and intuitions, but I think the needed intuitions are reasonable and an update from Bio-Anchors-ignorant starting positions is warranted.
Thanks for the answer!
Unfortunately, I don’t have the time at the moment to answer in detail and have more of a conversation, as I’m fully focused on writing a long sequence about pushing for pluralism in alignment and extracting the core problem out of all the implementation details and additional assumption. I plan on going back to analyzing timeline research in the future, and will probably give better answers then.
That being said, here are quick fire thoughts:
I used the evolution case because I consider it the most obvious/straightforward case, in that it sounds so large that everyone instantly assumes that it gives you an upper bound.
My general impression about this report (and one I expect Yudkowsky to share) is that it didn’t made me update at all. I already updated from GPT and GPT3, and I didn’t find new bits of evidence in the report and the discussions around it, despite the length of it. My current impression (please bear in mind that I haven’t taken the time to study the report from that angle, so I might change my stance) is that this report, much like a lot of timeline work, seems like it takes as input a lot of assumption, and gives as output far less than was assumed. It’s the opposite of compression — a lot of assumptions are needed to conclude things that aren’t that strong and constraining.