Response to Quintin Pope's Evolution Provides No Evidence For the Sharp Left Turn

Zvi

Response to: Evolution Provides No Evidence For the Sharp Left Turn, due to it winning first prize in The Open Philanthropy Worldviews contest.

Quintin’s post is an argument about a key historical reference class and what it tells us about AI. Instead of arguing that the reference makes his point, he is instead arguing that it doesn’t make anyone’s point - that we understand the reasons for humanity’s sudden growth in capabilities. He says this jump was caused by gaining access to cultural transmission which allowed partial preservation of in-lifetime learning across generations, which was a vast efficiency gain that fully explains the orders of magnitude jump in the expansion of human capabilities. Since AIs already preserve their metaphorical in-lifetime learning across their metaphorical generations, he argues, this does not apply to AI.

This last paragraph makes an extremely important claim that I want to ensure I convey fully:
- IF we understand the mechanism behind humanity's sharp left turn with respect to evolution
- AND that mechanism is inapplicable to AI development
- THEN, there's no reason to reference evolution at all when forecasting AI development rates, not as evidence for a sharp left turn, not as an "illustrative example" of some mechanism / intuition which might supposedly lead to a sharp left turn in AI development, not for anything.

That seems like quite a leap. If there is one particular development in humanity’s history that we can fully explain, we should then not cite evolution in any way, as an argument for anything?

If we applied this standard to other forms of reference class arguments, then presumably we would throw most or almost all of them out as well - anything where the particular mechanism was understood, and didn’t directly apply to AI, would not count. I do not see Quintin or other skeptics proposing this standard of evidence more generally, nor do I think it would make sense.

He then goes on to make another very broad claim.

In order to experience a sharp left turn that arose due to the same mechanistic reasons as the sharp left turn of human evolution, an AI developer would have to:
Deliberately create a (very obvious^[2]) inner optimizer, whose inner loss function includes no mention of human values / objectives.^[3]
Grant that inner optimizer ~billions of times greater optimization power than the outer optimizer.^[4]
Let the inner optimizer run freely without any supervision, limits or interventions from the outer optimizer.^[5]
This is the AI development equivalent of using landmines as hubcaps.

There are a number of extra things snuck in here that seem unnecessary.

Start with ‘deliberately.’ Why would that matter? Either it gets created or it doesn’t. Same with obvious, physics does not care what is obvious. We already presumably have what some of us would call obvious inner optimizers that are being simulated inside (e.g.) GPT-4 in order to predict humans that optimize for things. Did we create them deliberately?

Why does it matter whether their inner loss function ‘mentions’ human values or objectives? This seems like a non-sequitur. It seems highly unlikely that the exact intended (let alone resultant) target of the optimizer will be ‘human values’ generally, even if we knew how to specify that or what it even means, whether or not the optimizer was created intentionally.

Step two seems rather arbitrary. Why billions? Why is it not sufficient that it be superior at the relevant optimizations? This is a strange isolated demand for matching order of magnitude ratios. Quintin also seems (in a following paragraph) to only want to count explicit and intentionally applied optimization pressure that targets the inner optimizer, as opposed to the effective impact of whatever it is you do.

Step three does not seem necessary at all. It does seem like currently we are doing exactly this, but even if we didn’t, the inner optimizer has more optimization pressure working for it in the relevant areas, so why would we presume that the outer optimizer would be able to supervise it effectively or otherwise keep it in check? At most, we need the outer optimizer to not be a sufficiently effective control.

(If one wishes optionally to use the metaphor we are debating, reproductive fitness and survival indeed supervises, limits and intervenes on culture, and that has not proven a sufficiently effective way to align culture to reproductive fitness, although it very much does shape it in highly fundamental ways continuously. Also note that it did a much better job of this when culture moved relatively slowly in the past, and now in the future with faster cultural evolution relative to human lifecycles, we see far more people in cultures that are very bad at reproductive fitness - in the past we had such cultures (e.g. monastic forms of religions like Christianity) but they self-limited in size.)

I would also note that, if you discover (as in Quintin’s example of Evo-inc) that major corporations are going around using landmines as hubcaps, and that they indeed managed to gain dominant car market share and build the world’s most functional cars until recently, that is indeed a valuable piece of information about the world, and whether you should trust corporations or other humans to be able to make good choices, realize obvious dangers and build safe objects in general. Why would you think that such evidence should be ignored?

Quintin then proposes the two ways he sees fast takeoff as still possible.

AIs contributing to AI capabilities research, producing a positive feedback loop with a sharp upwards kink around the time that AI contributions exceed human contributions.
AIs deliberately seeking out new training data that grant them useful capabilities. E.g., an AI trying to improve its bioengineering capabilities may set up a very fast cycle of gathering and analyzing new biological data, which significantly outpaces the rate of human scientific innovation.

I would argue that ‘AIs contribute to AI capabilities research’ is highly analogous to ‘humans contribute to figuring out how to train other humans.’ And that ‘AIs seeking out new training data’ is highly analogous to ‘humans creating bespoke training data to use to train other people especially their children via culture’ which are exactly the mechanisms Quintin is describing humans as using to make a sharp left turn.

Here are four alignment-relevant implications:
Takeoff is less abrupt. Both of the above mechanisms are vaguely similar to how human cultural development allowed us to jump forwards in capabilities by feeding the outputs of one generation into the “training data” of the next generation. However, I expect that neither mechanism will produce as much of a relative jump in AI capabilities, as cultural development produced in humans. Neither mechanism would suddenly unleash an optimizer multiple orders of magnitude faster than anything that came before, as was the case when humans transitioned from biological evolution to cultural development.
Takeoff becomes easier to navigate. These specific mechanisms of capabilities advance probably both allow for iteration and experimentation. We currently have examples of both AI capabilities advances and of online learning / exploration processes. We can run experiments on current systems to assess the alignment risks posed by both these sources of capabilities improvement.
Capabilities gains are less general. "capabilities generalize further than alignment" is a common refrain in discussions about the sharp left turn. Usually, this claim is justified by making an analogy to how human capabilities started to quickly generalize across many domains simultaneously.
Alignment probably generalizes pretty well. Speaking of alignment techniques failing, I expect alignment techniques to mostly generalize across capabilities jumps caused by either of the above mechanisms for sudden capabilities gain.

Quintin acknowledges the similarity, but says this would not result in an orders of magnitude speedup. Why not?

Ignore the evolution parallel here, and look only at the scenario offered. What happens when the AI starts contributing to AI research? If the AI suddenly became able to perform as a human-level alignment researcher or capabilities researcher, only at the speed of an AI with many copies in parallel, would that not speed up development by orders of magnitude? Is this not Leike’s explicit plan for Superalignment, with the hope that we could then shift enough resources into alignment to keep pace?

One could say ‘first the AI will speed up research by automating only some roles somewhat, then more roles more, so it won’t be multiple orders of magnitude at the exact same time’ but so what? The timelines this implies do not seem so different from the timeline jumps in evolution. We would still be talking (in approximate terms throughout, no need to get pedantic) about takeoff to vast superintelligence in a matter of years at most, versus a prior human information age that lasted decades, versus industrial civilization lasting centuries, versus agricultural civilization lasting millennia, versus cultural transmission lasting tens of thousands, homo sapiens hundreds of thousands, human-style primates millions, primates in general tens of millions, land animals hundreds of millions, life and Earth billions, the universe tens of billions? Presumably with a ‘slow takeoff’ period of years as AIs start to accelerate work, then a period of months when humans are mostly out of the loop, then… something else?

That seems like a sharp enough left turn to me.

The second distinction he mentions is that this allows more iteration and experimentation. Well, maybe. In some ways, for some period. But the whole idea of ‘we can run alignment experiments on current systems, before they are dangerously general, and that will tell us what applies in the future’ assumes the conclusion.

The third distinction claims that capabilities gains will be less general. Why? Are cultural transmission gains general in this sense, or specific? Except that enough of that then effectively generalized. Humans, indeed, have continuously gained new capabilities, then been bottlenecked due to lack of other capabilities, then used their new capabilities to solve the next bottleneck. I don’t see why this time is different, or why you wouldn’t see a human-level-of-generality leap to generality from the dynamics Quintin is describing. I see nothing in his evolutionary arguments here as reason to not expect that. There are reasons for or against expecting more or less such generality, but mostly they aren’t covered here, and seem orthogonal to the discussion.

If anything, arguing that our generality came from human scaffolding and iterated design seems like an argument in favor of expecting AIs to become more general.

The fourth claim is made prior to its justification, which is in the later sections.

As a general note, these sections seem mostly to be making a general alignment is easy, alignment-by-default claim, rather than being about what evolution offers evidence for, and I would have liked to see them presented as a distinct post given how big and central and complex and disputed is the claim here.

He starts with an analogous claim to his main claim, that humans being clearly misaligned with genetic fitness is not evidence that we should expect such alignment issues in AIs. His argument (without diving into his earlier linked post) seems to be that humans are fresh instances trained on new data, so of course we expect different alignment and different behavior.

But if you believe that, you are saying that humans are fresh versions of the system. You are entirely throwing out from your definition of ‘the system’ all of the outer alignment and evolutionary data, entirely, saying it does not matter, that only the inner optimizer matters. In which case, yes, that does fully explain the differences. But the parallel here does not seem heartening. It is saying that the outcome is entirely dependent on the metaphorical inner optimizer, and what the system is aligned to will depend heavily on the details of the training data it is fed and the conditions under which it is trained, and what capabilities it has during that process, and so on. Then we will train new more capable systems in new ways with new data using new techniques, in an iterated way, in similar fashion. How should this make us feel better about the situation and its likely results?

Once again, there is the background presumption that things like ‘extreme misgeneralization’ need to happen for us to be in trouble. I find these attempts to sneak in a form of alignment-by-default to be extremely frustrating.

The next section seems to argue that because alignment techniques work on a variety of existing training regimes all of similar capabilities level, we should expect alignment techniques to extend to future systems with greater capabilities. I suppose this is not zero evidence. The opposite result was possible and would have been bad news, so this must be good news. The case here still ignores the entire reason why I and others expect the techniques to fail, or why evolutionary arguments would expect it to fail, in the future.

He closes by arguing that iteratively improving training data also exhibits important differences from cultural development, sufficient to ignore the evolutionary evidence as not meaningful in this context. I do not agree. Even if I did agree, I do not see how that would justify his broader optimism expressed here:

The odds of any given subset of model data catastrophically interfering with our current alignment techniques cannot be that high, otherwise our current alignment techniques wouldn't work on our current models.

Once again, the whole argument is that the current techniques will break down when capabilities advance. Saying aberrant data does not usually break alignment at current capability levels is some evidence of robustness, given that the opposite would have been evidence against it and was certainly plausible before we experimented, but again this ignores the claimed mechanisms. It also ignores that the current style of alignment does indeed seem porous and imprecise, in a way that is acceptable at current capabilities levels but that would be highly scary at sufficiently high capabilities levels. My model of how this works is that the system will indeed incorporate all the data, and will get more efficient and effective at this as capabilities advance, but this does not currently have that much practical import in many cases.

I do think there are some good points here drawing distinctions between the evolutionary and artificial cases, including details I hadn’t considered. However I also think there are a lot of statements I disagree with strongly, or that seem overstated, or that seemed to sneak in assumptions I disagree with, often about alignment and its difficulties and default outcomes.

The central claim, that evolution provides no evidence for the sharp left turn, definitely seems false to me, or at least strongly overstated. Even if I bought the individual arguments in the post fully, which I do not, that is not how evidence works. Consider the counterfactual. If we had not seen a sharp left turn in evolution, civilization had taken millions of years to develop to this point with gradual steady capability gains, and we saw humans exhibiting strong conscious optimization mostly for their genetic fitness, it would seem crazy not to change our beliefs at all about what is to come compared to what we do observe. Thus, evidence.

I would also note that Quintin in my experience often cites parallels between humans and AIs as a reason to expect good outcomes from AI due to convergent outcomes, in circumstances where it would be easy to find many similar distinctions between the two cases. Here, although I disagree with his conclusions, I agree with him that the human case provides important evidence.

In the generally strong comments to OP, Steven Byrnes notes that current LLM systems are incapable of autonomous learning, versus humans and AlphaZero which are, and that we should expect this ability in future LLMs at some point. Constitutional AI is not mentioned, but so far it has only been useful for alignment rather than capabilities, and Quintin suggests autonomous learning mostly relies upon a gap between generation and discernment in favor of discernment being easier. I think this is an important point, while noting that what matters is ability to discern between usefully outputs at all, rather than it being easier, which is an area where I keep trying to put my finger on writing down the key dynamics and so far falling short.

Response to: Evolution Provides No Evidence For the Sharp Left Turn, due to it winning first prize in The Open Philanthropy Worldviews contest.

This last paragraph makes an extremely important claim that I want to ensure I convey fully:
- IF we understand the mechanism behind humanity's sharp left turn with respect to evolution
- AND that mechanism is inapplicable to AI development
- THEN, there's no reason to reference evolution at all when forecasting AI development rates, not as evidence for a sharp left turn, not as an "illustrative example" of some mechanism / intuition which might supposedly lead to a sharp left turn in AI development, not for anything.

That seems like quite a leap. If there is one particular development in humanity’s history that we can fully explain, we should then not cite evolution in any way, as an argument for anything?

He then goes on to make another very broad claim.

In order to experience a sharp left turn that arose due to the same mechanistic reasons as the sharp left turn of human evolution, an AI developer would have to:
Deliberately create a (very obvious^[2]) inner optimizer, whose inner loss function includes no mention of human values / objectives.^[3]
Grant that inner optimizer ~billions of times greater optimization power than the outer optimizer.^[4]
Let the inner optimizer run freely without any supervision, limits or interventions from the outer optimizer.^[5]
This is the AI development equivalent of using landmines as hubcaps.

There are a number of extra things snuck in here that seem unnecessary.

Quintin then proposes the two ways he sees fast takeoff as still possible.

AIs contributing to AI capabilities research, producing a positive feedback loop with a sharp upwards kink around the time that AI contributions exceed human contributions.
AIs deliberately seeking out new training data that grant them useful capabilities. E.g., an AI trying to improve its bioengineering capabilities may set up a very fast cycle of gathering and analyzing new biological data, which significantly outpaces the rate of human scientific innovation.

Here are four alignment-relevant implications:
Takeoff is less abrupt. Both of the above mechanisms are vaguely similar to how human cultural development allowed us to jump forwards in capabilities by feeding the outputs of one generation into the “training data” of the next generation. However, I expect that neither mechanism will produce as much of a relative jump in AI capabilities, as cultural development produced in humans. Neither mechanism would suddenly unleash an optimizer multiple orders of magnitude faster than anything that came before, as was the case when humans transitioned from biological evolution to cultural development.
Takeoff becomes easier to navigate. These specific mechanisms of capabilities advance probably both allow for iteration and experimentation. We currently have examples of both AI capabilities advances and of online learning / exploration processes. We can run experiments on current systems to assess the alignment risks posed by both these sources of capabilities improvement.
Capabilities gains are less general. "capabilities generalize further than alignment" is a common refrain in discussions about the sharp left turn. Usually, this claim is justified by making an analogy to how human capabilities started to quickly generalize across many domains simultaneously.
Alignment probably generalizes pretty well. Speaking of alignment techniques failing, I expect alignment techniques to mostly generalize across capabilities jumps caused by either of the above mechanisms for sudden capabilities gain.

Quintin acknowledges the similarity, but says this would not result in an orders of magnitude speedup. Why not?

That seems like a sharp enough left turn to me.

If anything, arguing that our generality came from human scaffolding and iterated design seems like an argument in favor of expecting AIs to become more general.

The fourth claim is made prior to its justification, which is in the later sections.

The odds of any given subset of model data catastrophically interfering with our current alignment techniques cannot be that high, otherwise our current alignment techniques wouldn't work on our current models.

I think this post greatly misunderstands mine.

Firstly, I'd like to address the question of epistemics.

When I said "there's no reason to reference evolution at all when forecasting AI development rates", I was referring to two patterns of argument that I think are incorrect: (1) using the human sharp left turn as evidence for an AI sharp left turn, and (2) attempting to "rescue" human evolution as an informative analogy for other aspects of AI development.

(Note: I think Zvi did follow my argument for not drawing inferences about the odds of the sharp left turn specifically. I'm still starting by clarifying pattern 1 in order to set things up to better explain pattern 2.)

Pattern 1: using the human sharp left turn as evidence for an AI sharp left turn.

The original sharp left turn post claims that there are general factors about the structure and dynamics of optimization processes which both caused the evolutionary sharp left turn, and will go on to cause another sharp left turn in AI systems. The entire point of Nate referencing evolution is to provide evidence for these factors.

My counterclaim is that the causal processes responsible for the evolutionary sharp left turn are almost entirely distinct from anything present in AI development, and so the evolutionary outcome is basically irrelevant for thinking about AI.

From my perspective, this is just how normal Bayesian reasoning works. If Nate says:

P(human SLT | general factors that cause SLTs) ~= 1

P(human SLT | NOT general factors that cause SLTs) ~= 0

then observing the human SLT is very strong evidence for there being general factors that cause SLTs in different contexts than evolution.

OTOH, I am saying:

P(human SLT | NOT general factors that cause SLTs) ~= 1

And so observing the human SLT is no evidence for such general factors.

Pattern 2: attempting to "rescue" human evolution as an informative analogy for other aspects of AI development.

When I explain my counterargument to pattern 1 to people in person, they will very often try to "rescue" evolution as a worthwhile analogy for thinking about AI development. E.g., they'll change the analogy so it's the programmers who are in a role comparable to evolution, rather than SGD.

I claim that such attempted inferences also fail, for the same reason as argument pattern 1 above fails: the relevant portions of the causal graph driving evolutionary outcomes is extremely different from the causal graph driving AI outcomes, such that it's not useful to use evolution as evidence to make inferences about nodes in the AI outcomes causal graph. E.g., the causal factors that drive programmers to choose a given optimizer are very different from the factors that cause evolution to "choose" a given optimizer. Similarly, evolution is not a human organization that makes decisions based on causal factors that influence human organizations, so you should look at evolution for evidence of organization-level failures that might promote a sharp left turn in AI.

Making this point was the purpose of the "alien space clowns" / EVO-Inc example. It was intended to provide a concrete example of two superficially similar seeming situations, where actually their causal structures are completely distinct, such that there are no useful updates to make from EVO-Inc's outcomes to other automakers. When Zvi says:

I would also note that, if you discover (as in Quintin’s example of Evo-inc) that major corporations are going around using landmines as hubcaps, and that they indeed managed to gain dominant car market share and build the world’s most functional cars until recently, that is indeed a valuable piece of information about the world, and whether you should trust corporations or other humans to be able to make good choices, realize obvious dangers and build safe objects in general. Why would you think that such evidence should be ignored?

Zvi is proposing that there are common causal factors that led to the alien clowns producing dangerous cars, and could also play a similar role in causing other automakers to make unsafe vehicles, such that Evo-Inc's outcomes provide useful updates for predicting other automakers' outcomes. This is what I'm saying is false about evolution versus AI development.

At this point, I should preempt a potential confusion: it's not the case that AI development and human evolution share zero causal factors! To give a trivial example, both rely on the same physical laws. What prevents there being useful updates from evolution to AI development is the different structure of the causal graphs. When you update your estimates for the shared factors between the graphs using evidence from evolution, this leads to trivial or obvious implications for AI development, because the shared causal factors play different roles in the two graphs. You can have an entirely "benign" causal graph for AI development, which predicts zero alignment issues for AI development, yet when you build the differently structured causal graph for human evolution, it still predicts the same sharp left turn, despite some of the causal factors being shared between the graphs.

This is why inferences from evolutionary outcomes to AI development don't work. Propagating belief updates through the evolution graph doesn't change any of the common variables away from settings which are benign in the AI development graph, since those settings already predict a sharp left turn when they're used in the evolution graph.

Concrete example 1: We know from AI development that having a more powerful optimizer, running for more steps, leads to more progress. Applying this causal factor to the AI development graph basically predicts "scaling laws will continue", which is just a continuation of the current trajectory. Applying the same factor to the evolution graph, combined with the evolution-specific fact of cultural transmission enabling a (relatively) sudden unleashing of ~9 OOM more effectively leveraged optimization power in a very short period of time, predicts an extremely sharp increase in the rate of progress.

Concrete example 2: One general hypothesis you could have about RL agents is "RL agents just do what they're trained to do, without any weirdness". (To be clear, I'm not endorsing this hypothesis. I think it's much closer to being true than most on LW, but still false.) In the context of AI development, this has pretty benign implications. In the context of evolution, due to the bi-level nature of its optimization process and the different data that different generations are "trained" on, this causal factor in the evolution graph predicts significant divergence between the behaviors of ancestral and modern humans.

Zvi says this is an uncommon standard of epistemics, for there to be no useful inferences from one set of observations (evolutionary outcomes) to another (AI outcomes). I completely disagree. For the vast majority of possible pairs of observations, there are not useful inferences to draw. The pattern of dust specks on my pillow is not a useful reference point for making inferences about the state of the North Korean nuclear weapons program. The relationship between AI development and human evolution is not exceptional in this regard.

Secondly, I'd like to address a common pattern in a lot of Zvi's criticisms.

My post has a unifying argumentative structure that Zvi seems to almost completely miss. This leads to a very annoying dynamic where:

My post makes a claim / argument that serves a very specific role in the context of the larger structure.
Zvi misses that context, and interprets the claim / argument as making some broader claim about alignment in general.
Zvi complains that I'm over-claiming, being too general, or should split the post along the separate claims Zvi (falsely) believes I'm making.

The unifying argumentative structure of my post is as follows:

Evolution’s sharp left turn happened for evolution-specific reasons
- Describes the causal structure of evolution's sharp left turn.
Don't misgeneralize from evolution to AI
- Argues you shouldn't generalize between things with very different causal structures.
Fast takeoff is still possible
- Clarifies that I am not arguing against fast takeoff, and that fast takeoff can happen without a sharp left turn.
- Proposes two AI-specific causal mechanisms that could cause a fast takeoff.
- Discusses why it's alignment relevant if fast takeoff happens because of either of the two mechanisms previously mentioned.
Will alignment generalize across sudden capabilities jumps?
- Human "misalignment" with inclusive genetic fitness provides no evidence for AI misalignment
  - Somewhat awkwardly shoehorns in the argument that evolution also provides no evidence for inner alignment failures in general.
- Capabilities jumps due to AI driving AI capabilities research
  - Argues that this specific fast takeoff mechanism will not itself cause a sharp left turn / alignment failure
- Capabilities jumps due to AI iteratively refining its training data
  - Argues that this specific fast takeoff mechanism will not itself cause a sharp left turn / alignment failure
Conclusion

Having outlined my argumentative structure, I'll highlight some examples where Zvi's criticisms fall into the previously mentioned dynamic.

[Zvi] He then goes on to make another very broad claim.
[Zvi quoting me] > In order to experience a sharp left turn that arose due to the same mechanistic reasons as the sharp left turn of human evolution, an AI developer would have to:
[I list some ways one could produce an ML training process that's actually similar to human evolution in the relevant sense that would lead to an evolution-like sharp left turn at some point]
[Zvi criticizes the above list on the grounds that inner misalignment could occur under a much broader range of circumstances than I describe]

(I added the bolding)

The issue here is that the list in question is specifically for sharp left turns that arise "due to the same mechanistic reasons as the sharp left turn of human evolution", as I very specifically said in my original post. I'm not talking about inner alignment in general. I'm not even talking about sharp left turn threat scenarios in general! I'm talking very specifically about how the current AI paradigm would have to change before it had a mechanistic structure sufficiently similar to human evolution that I think a sharp left turn would occur "due to the same mechanistic reasons as the sharp left turn of human evolution".

As a general note, these sections seem mostly to be making a general alignment is easy, alignment-by-default claim, rather than being about what evolution offers evidence for, and I would have liked to see them presented as a distinct post given how big and central and complex and disputed is the claim here.

That is emphatically not what those sections are arguing for. The purpose of these sections is to describe two non-sharp left turn causing mechanisms for fast takeoff, in order to better illustrate that fast takeoff != sharp left turn. Each section specifically focuses on a particular mechanism of fast takeoff, and argues that said mechanism will not, in and of itself, lead to misalignment. You can still believe a fast takeoff driven by that mechanism will lead to misalignment for other reasons (e.g., a causal graph that looks like: "(fast takeoff mechanism) -> (capabilities) -> (something else) -> (misalignment)"), if, say, you think there's another causal mechanism driving misalignment, such that the fast takeoff mechanism's only contribution to misalignment was to advance capabilities in a manner that failed to address that other mechanism.

These sections are not arguing about the ease of alignment in general, but about the consequence of one specific process.

The next section seems to argue that because alignment techniques work on a variety of existing training regimes all of similar capabilities level, we should expect alignment techniques to extend to future systems with greater capabilities.

That is, even more emphatically, not what that specific section is arguing for. This section focuses specifically on the "AIs do AI capabilities research" mechanism of fast takeoff, and argues that it will not itself cause misalignment. Its purpose is specific to the context in which I use it: to address the causal influence of (AIs do capabilities research) directly to (misalignment), not to argue about the odds of misalignment in general.

Further, the argument that section made wasn't:

because alignment techniques work on a variety of existing training regimes all of similar capabilities level, we should expect alignment techniques to extend to future systems

It was:

alignment techniques already generalize across human contributions to AI capability research. Let’s consider eight specific alignment techniques:
[list of alignment techniques]
and eleven recent capabilities advances:
[list of capabilities techniques]
I don’t expect catastrophic interference between any pair of these alignment techniques and capabilities advances.

And so, if you think AIs doing capabilities will be like humans doing capabilities research, but faster, then there will be a bunch of capabilities and alignment techniques, and the question is how much the capabilities techniques will interfere with the alignment techniques. Based on current data, the interference seems small and manageable. This is the trend being projected forwards, the lack of empirical interference between current capabilities and alignment (despite, as I note in my post, current capabilities techniques putting ~zero effort into not interfering with alignment techniques, an obviously dumb oversight which we haven't corrected because it turns out we don't even need to do so).

Once again, I emphasize that this is not a general argument about alignment, which can be detached from the rest of the post. It's extremely specific to the mechanism for fast takeoff being analyzed, which is only being analyzed to further explore the connection between fast takeoff mechanisms and the odds of a sharp left turn.

He closes by arguing that iteratively improving training data also exhibits important differences from cultural development, sufficient to ignore the evolutionary evidence as not meaningful in this context. I do not agree. Even if I did agree, I do not see how that would justify his broader optimism expressed here:

This part is a separate analysis of a different fast takeoff causal mechanism, arguing that it will not, itself cause misalignment either. Its purpose and structure mirrors that of the argument I clarified above, but focused on a different mechanism. It's not a continuation of a previous (non-existent) "alignment is easy in general" argument.

Thirdly, I'd like to make some random additional commentary.

I would argue that ‘AIs contribute to AI capabilities research’ is highly analogous to ‘humans contribute to figuring out how to train other humans.’ And that ‘AIs seeking out new training data’ is highly analogous to ‘humans creating bespoke training data to use to train other people especially their children via culture’ which are exactly the mechanisms Quintin is describing humans as using to make a sharp left turn.

The degree of similarity is arguable. I think, and said in the original article, that similarity is low for the first mechanism and moderate for the second.

However, the appropriate way to estimate the odds of a given fast takeoff mechanism leading to AI misalignment is not to estimate the similarity between that mechanism and what happened during human evolution, then assign misalignment risk to the mechanism in proportion to the estimated similarity. Rather, the correct approach is to build detailed causal models of how both human evolution and AI development work, propagate the evidence from human evolutionary outcomes back through your human evolution causal model to update relevant latent variables in that causal model, transfer those updates to any of the AI development causal model's latent variables which are also in the human evolution causal model, and finally estimate the new misalignment risk implied by the updated variables of the AI development model.

I discussed this in more detail in the first part of my comment, but whenever I do this, I find that the transfer from (observations of evolutionary outcomes) to (predictions about AI development) are pretty trivial or obvious, leading to such groundbreaking insights as:

More optimization power leads to faster progress
Human level general intelligence is possible
Neural architecture search is a bad thing to spend most of your compute on
Retraining a fresh instance of your architecture from scratch on different data will lead to different behavior

That seems like a sharp enough left turn to me.

A sharp left turn is more than just a fast takeoff. It's the combined sudden increase in AI generality and breaking of previously existing alignment properties.

...humans being clearly misaligned with genetic fitness is not evidence that we should expect such alignment issues in AIs. His argument (without diving into his earlier linked post) seems to be that humans are fresh instances trained on new data, so of course we expect different alignment and different behavior.
But if you believe that, you are saying that humans are fresh versions of the system. You are entirely throwing out from your definition of ‘the system’ all of the outer alignment and evolutionary data, entirely, saying it does not matter, that only the inner optimizer matters. In which case, yes, that does fully explain the differences. But the parallel here does not seem heartening. It is saying that the outcome is entirely dependent on the metaphorical inner optimizer, and what the system is aligned to will depend heavily on the details of the training data it is fed and the conditions under which it is trained, and what capabilities it has during that process, and so on. Then we will train new more capable systems in new ways with new data using new techniques, in an iterated way, in similar fashion. How should this make us feel better about the situation and its likely results?

I find this perspective baffling. Where else do the alignment properties of a system derive from? If you have a causal structure like

(programmers) -> (training data, training conditions, learning dynamics, etc) -> (alignment properties)

then setting the value of the middle node will of course screen off the causal influence of the (programmers) node.

A possible clarification: in the context of my post when discussing evolution, "inner optimizer" means the brain's "base" optimization process, not the human values / intelligence that arises from that process. The mechanistically most similar thing in AI development to that meaning of the word "inner optimizer" is the "base" training process: the combination of training data, base optimizer, training process, architecture, etc. It doesn't mean the cognitive system that arises as a consequence of running that training process.

Consider the counterfactual. If we had not seen a sharp left turn in evolution, civilization had taken millions of years to develop to this point with gradual steady capability gains, and we saw humans exhibiting strong conscious optimization mostly for their genetic fitness, it would seem crazy not to change our beliefs at all about what is to come compared to what we do observe. Thus, evidence.

I think Zvi is describing a ~impossible world. I think this world would basically break ~all my models on how optimizing processes gain capabilities. My new odds of an AI sharp left turn would depend on the new models I made in this world, which in turn would depend on unspecified details of how human civilization's / AI progress happens in this world.

I would also note that Quintin in my experience often cites parallels between humans and AIs as a reason to expect good outcomes from AI due to convergent outcomes, in circumstances where it would be easy to find many similar distinctions between the two cases. Here, although I disagree with his conclusions, I agree with him that the human case provides important evidence.

Once again, it's not the degree of similarity that determines what inferences are appropriate. It's the relative structure of the two causal graphs for the processes in question. The graphs for the human brain and current AI systems are obviously not the same, but they share latent variables that serve similar roles in determining outcomes, in a way that the bi-level structure of evolution's causal graph largely prevents. E.g., Steven Byrnes has a whole sequence which discusses the brain's learning process, and while there are lots of differences between the brain and current AI designs, there are also shared building blocks whose behaviors are driven by common causal factors. The key difference with evolution is that, once one updates the shared variables from looking at human brain outcomes and applies those updates to the AI development graph, there are non-trivial / obvious implications. Thus, one can draw relevant inferences by observing human outcomes.

Concrete example 1: brains use a local, non-gradient based optimization process to minimize predictive error, so there exists some non-SGD update rules that are competitive with SGD (on brainlike architectures, at least).

Concrete example 2: brains don't require GPT-4 level volumes of training data, so there exist architectures with vastly more data-friendly scaling laws than GPT-4's scaling.

In the generally strong comments to OP, Steven Byrnes notes that current LLM systems are incapable of autonomous learning, versus humans and AlphaZero which are, and that we should expect this ability in future LLMs at some point. Constitutional AI is not mentioned, but so far it has only been useful for alignment rather than capabilities, and Quintin suggests autonomous learning mostly relies upon a gap between generation and discernment in favor of discernment being easier. I think this is an important point, while noting that what matters is ability to discern between usefully outputs at all, rather than it being easier, which is an area where I keep trying to put my finger on writing down the key dynamics and so far falling short.

What I specifically said was:

Autonomous learning basically requires there to be a generator-discriminator gap in the domain in question, i.e., that the agent trying to improve its capabilities in said domain has to be better able to tell the difference between its own good and bad outputs.

I realize this is accidentally sounds like it's saying two things at once (that autonomous learning relies on the generator-discriminator gap of the domain, and then that it relies on the gap for the specific agent (or system in general)). To clarify, I think it's the agent's capabilities that matter, that the domain determines how likely the agent is to have a persistent gap between generation and discrimination, and I don't think the (basic) dynamics are too difficult to write down.

You start with a model M and initial data distribution D. You train M on D such that M is now a model of D. You can now sample from M, and those samples will (roughly) have whatever range of capabilities were to be found in D.

Now, suppose you have some classifier, C, which is able to usefully distinguish samples from M on the basis of that sample's specific level of capabilities. Note that C doesn't have to just be an ML model. It could be any process at all, including "ask a human", "interpret the sample as a computer program trying to solve some problem, run the program, and score the output", etc.

Having C allows you to sample from a version of M's output distribution that has been "updated" on C, by continuously sampling from M until a sample scores well on C. This lets you create a new dataset D', which you can then train M' on to produce a model of the updated distribution.

So long as C is able to provide classification scores which actually reflect a higher level of capabilities among the samples from M / M' / M'' / etc, you can repeat this process to continually crank up the capabilities. If your classifier C was some finetune of M, then you can even create a new C' off of M', and potentially improve the classifier along with your generator. In most domains though, classifier scores will eventually begin to diverge from the qualities that actually make an output good / high capability, and you'll eventually stop benefiting from this process.

This process goes further in domains where it's easier to distinguish generations by their quality. Chess / other board games are extreme outliers in this regard, since you can always tell which of two players actually won the game. Thus, the game rules act as a (pairwise) infallible classifier of relative capabilities. There's some slight complexity around that last point, since a given trajectory could falsely appear good by beating an even worse / non-representative policy, but modern self-play approaches address such issues by testing model versions against a variety of opponents (mostly past versions of themselves) to ensure continual real progress. Pure math proofs is another similarly skewed domain, where building a robust verifier (i.e., a classifier) of proofs is easy. That's why Steven was able to use it as a valid example of where self-play gets you very far.

Most important real world domains do not work like this. E.g., if there were a robust, easy-to-query process that could classify which of two scientific theories / engineering designs / military strategies / etc was actually better, the world would look extremely different.

There are other issues I have with this post, but my reply is already longer than the entire original post, so I'll stop here, rather than, say, adding an entire additional section on my models of takeoff speed for AIs versus evolution (which I'll admit probably should have another post to go with it).

46

Response to Quintin Pope's Evolution Provides No Evidence For the Sharp Left Turn

46

46

Response to Quintin Pope's Evolution Provides No Evidence For the Sharp Left Turn

46