Thanks for writing this! I appreciate the effort to make your perspective more transparent (and implicitly Anthropic's perspective as well). In this comment, I'll explain my two most important concerns with this proposal:

• Fully state-proof security seems crucial at ASL-4, not only at ASL-5
• You should have a clear exit plan and I disagree with what seems to be the proposal (fully deferring to the government on handling ASL-5 seems insufficient)

I have a variety of other takes on this proposal as well as various notes, but I decided to start by just writing up these two thoughts. I'll very likely add more comments in a bit.

Fully state-proof security seems crucial at ASL-4, not only at ASL-5

When you have AIs which can massively accelerate total AI capabilities R&D production (>5x)^[1], I think it is crucial that such systems are secure against very high-resource state actor attacks. (From the RAND report, this would be >=SL5^[2].) This checklist seems to assume that this level of security isn't needed until ASL-5, but you also say that ASL-5 is "broadly superhuman" so it seems likely that dramatic acceleration occurs before then. You also say various other things that seem to imply that early TAI could dramatically accelerate AI R&D.

I think having extreme security at the point of substantial acceleration is the most important intervention on current margins in short timelines. So, I think it is important to ensure that this is correctly timed.

As far as the ASL-4 security bar, you say:

early TAI will likely require a stronger ASL-4 standard, under which we need to be capable of defending against all but the most sophisticated nation-state-level attacks

This seems to imply a level of security of around SL-4 from the RAND report which would be robust to routine state actor attacks, but not top priority attacks. This seems insufficient given the costs of such a system being stolen and how clearly appealing this would be as you note later:

We will need to be prepared for TAI-level model weights to be one of the most sought-after and geopolitically important resources in history.

This seems to imply that you'll need more than SL5 security!^[3]

You should have a clear exit plan and I disagree with what seems to be the proposal

You say that at ASL-5 (after TAI):

Governments and other important organizations will likely be heavily invested in AI outcomes, largely foreclosing the need for us to make major decisions on our own. By this point, in most possible worlds, the most important decisions that the organization is going to make have already been made.

For us to judge whether this is a good overall proposal, it would help to have a clear exit plan including an argument that this exit state is acceptable. This allows us to discuss whether this exit state actually is acceptable and to analyze whether the earlier steps will plausibly lead to this state.

Further, it seems likely that people writing plans and proposals now are also the plans that the government might end up using! (After all, who will the relevant people in the US government ask for help in figuring out what to do?)

As far as I can tell, the proposed exit state you're imagining is roughly "perfectly (scalably?) solve alignment (or just for substantially superhuman systems?) and then hand things off to the government":

So, before the end of Chapter 2, we will need to have either fully, perfectly solved the core challenges of alignment, or else have fully, perfectly solved some related (and almost as difficult) goal like corrigibility that rules out a catastrophic loss of control.

(The proposal is also that we'll have improved societal resilience and tried to address AI welfare concerns along the way. I left this out because it seemed less central.)

I worry about the proposal of "perfectly solve alignment", particularly because you didn't list any concrete plausible research bets which are being scoped out and tested in advance. (And my sense is that few plausible bets exist and all seem pretty likely to fail.)

Further, I think the default plan should be to ensure a delay (perhaps at least 5 years) prior to building wildly superhuman AI after full TAI. Wildly superhuman AI seems incredibly scary, even relative to AIs which are qualitatively comparably smart to top human experts. (This is not just for misalignment reasons, though this is part of it.) I think the "perfectly solve alignment then the government is in charge" plan plausibly leads to the default action being to build wildly superhuman AI as quickly as possible. So, I'd prefer a more specific plan which is opinionated about the transition to wildly superhuman AI.

My preferred exit plan is to build human-obsoleting AIs which are sufficiently aligned/trustworthy that we can safely defer to them even on tricky, high-stakes questions where we can't (or just don't) check their outputs. For AIs to be human-obsoleting, they would need to outcompete top human experts, and thus probably can't be much dumber than top human experts. Ideally, they also wouldn't be much smarter than top human experts and preferably notably dumber while compensating with speed and knowledge (though the capability profile of such systems might be very spiky in practice). Being able to defer to AIs to this extent (we trust them at least as much as well-regarded humans in terms of judgment and alignment) is stronger than just ruling out egregious misalignment (e.g. it requires that AIs are sufficiently philosophically competent and actually try on near-impossible-to-check questions), though I expect that ruling out egregious misalignment is the hardest part in practice. Further, we would aim to have more than 3 years of time prior to needing to build substantially superhuman AIs to remain competitive after the point where we have such human-obsoleting and deferrable AIs.

As part of achieving my proposed exit plan, I would also focus much more on buying time when AIs are this powerful or nearly this powerful. Using huge amounts of AI labor to buy time could be done prior to achieving the full desiderata of this exit plan using approaches like AI Control [LW · GW]. Part of this would involve increasing willingness to pay on coordination and non-proliferation such as making demonstrations of risks as you discuss in the section "Developing Clear Smoking Gun Demos for Emerging Risk Factors". (That said, this seems focused on speculative risks, and I'd also potentially expand this to demonstrations of the most concerning capabilities from a national security perspective.) But beyond increasing willingness to pay, I think it also seems likely to be important to work (using vast amounts of AI labor) on reducing the cost of coordination and non-proliferation such as by building better monitoring approaches (e.g., better satellite tracking of data centers), improving verification approaches, building up carrots for coordination, and potentially building up sticks to reduce the cost of enforcing non-proliferation.

I think this is a good proposal because it seems as though a high fraction of risk comes from building wildly superhuman AI and it seems much easier to mitigate risks prior to this point. The AIs we defer to could end up recommending a wide variety of proposals (buying more time, emulated minds, developing totally different AI paradigms), not just doing huge amounts of research into aligning superintelligence. Such AIs would always have an option of trying to run themselves much faster to accomplish very difficult research which requires substantial serial time. We wouldn't need to be able to check their work or their intermediate states which improves the situation considerably.

More generally, it just seems really heuristically scary to very quickly go from AIs which aren't much smarter than the best humans to AIs which are wildly smarter in only a few years. Edit: so it would be good to buy time, first for ensuring we have human obsoleting AIs we can defer to and then so that these AIs can have enough time to figure out what to do.

Buck and I are writing an overall short plan for (technical) AI safety and in this we'll discuss all aspects of this in more detail.

I left an earlier comment on more important and clearer points, but I thought I would also leave a comment with some more tentative remarks, explanations of where I'm confused, and notes.

The story for ASL-4 safety seems unclear and/or unlikely to provide a "reasonable" level of safety

In this checklist, perhaps the most important target for ASL-4 technical safety measures (not including security) is having the measures to ensure that ASL-4 is safe with respect to misalignment. From what I could tell, you were imagining:

• Hopefully mechanistic interpretability will allow for a high-confidence case for safety.
• If that fails or is insufficient, then we'll need other basic science such as "scaling trends of risk factors in model organisms, scaling trends of the effectiveness of oversight and monitoring, the basic science of generalization, novel honeypot-style evaluation methods, high-confidence 'nerfing' (i.e., capability deletion), and high-level less-mechanistic interpretability methods like influence functions"
• It was unclear to me whether you expected control-style cases to work for an ASL-4/TAI safety case or if you expected it to only work earlier.

I think mechanistic interpretability is unlikely to provide a high degree of assurance (<10% probability of a 10x risk reduction, and <20% probability of a 3x risk reduction where the risk reduction is relative to other more simple methods). So, I think the first bullet will likely be unimportant. Then, the question is whether the second bullet will suffice or whether you are leaning on control.

I was generally a bit unclear on what you were imagining given that you didn't describe a specific list of possible approaches and I generally didn't see a clear story for how the safety case would work. At a more basic level, I expect that the main hope for the first TAIs will end up being AI control [LW · GW] in short timelines, and this seems underemphasized if you think this, so likely we disagree or I ended up confused about what you're imagining.

Personally, I'd advocate for using roughly three pillars for ASL-4:

• AI control [LW · GW] which can hopefully provide a greater than 10x risk reduction given substantial effort on implementation and some tax. (And this risk reduction can plausibly be mostly pretty evaluable.)
• Model organisms style work where you look for evidence of egregious misalignment (both in constructed cases and by adversarially evaluating the actual production models you've deployed).
• Ad hoc methods that seem like they might help (aka the bag of tricks), but which aren't particularly principled and which might be very difficult to evaluate (e.g. coup probes, generally trying to make training less exploitable because maybe this reduces misalignment risk, perhaps influence functions, try random stuff on model organisms and hope for transfer).

It seems likely to me that this proposal I'm outlining doesn't provide a reasonable level of assurance (e.g. <0.5% takeover/escape/severe sabotage risk throughout ASL-4), but I think it could work at the start of ASL-4 and is reasonably likely to be the best we've got in short timelines.

Overall, I think that it will likely be quite hard to meet a reasonable level of assurance for ASL-4 with the technology we have at least in slightly more pessimistic worlds (worlds where there are some warning signs or the architecture is somewhat less favorable). So, plans should bear this in mind. I think extensive planning for when you can't make reasonable safety targets seem quite important, including plans for when you find smoking gun evidence of egregious misalignment or plans for when the evidence is more confusing, but our countermeasures and tests aren't sufficiently good to provide a reasonable degree of assurance.

I was confused by what capability level you were referring to by "early TAI" or I somewhat disagree with how lightly you treat TAI

You used the term "early TAI". I would have thought this meant the first TAI where you defined TAI to be an AI which is a drop-in replacement for human workers, including in AI R&D. However, in the sections "Largely Solving Alignment Fine-Tuning for Early TAI" and "Rendering Early TAI Reliably Harmless", you seemed to possibly imply that this was before TAI. In particular, you seemed to imply that scheming wouldn't be a risk at the start of TAI (seems unclear to me given that the AIs are comparable to top human experts!) and you seemed to imply that such AIs wouldn't speed up R&D that much (while I expect that drop-in replacements for top human AI researchers would pretty likely result in huge acceleration!).

Perhaps I was mostly confused by how you split things up across different headings?

This is also related to my earlier point on ASL-4 security [LW(p) · GW(p)].

"Intelligence explosion level" isn't likely to be a meaningful threshold and TAI will likely greatly accelerate AI R&D

You seem to define TAI as "AI that could form as a drop-in replacement for humans in all remote-work-friendly jobs, including AI R&D". This seems to imply that TAI would likely greatly accelerate AI R&D to the extent that it is possible to greatly accelerate with human labor (which seems like an assumption of the piece).

But later you say:

AI R&D is not automated to the point of allowing the kind of AI self-improvement that would lead to an intelligence explosion, if such a thing is possible, but AI-augmented R&D is very significantly speeding up progress on both AI capabilities and AI safety.

I would have guessed that for this definition and the assumptions of the piece, you would expect >10x acceleration of AI R&D (perhaps 30x) given the definition of TAI.

Further "allowing the kind of AI self-improvement that would lead to an intelligence explosion, if such a thing is possible" doesn't seem like an interesting or important bar to me. If progress has already accelerated and the prediction is that it will keep accelerating, then the intelligence explosion is already happening (though it is unclear what the full extent of the explosion will be).

You seem to have some idea in mind of "intelligence-explosion level", but it was unclear to me what this was supposed to mean.

Perhaps you mean something like "could the AIs fully autonomously do an intelligence explosion"? This seems like a mostly unimportant distinction given that projects can use human labor (even including rogue AI-run projects). I think a more natural question is how much the AIs can accelerate things over a human baseline and also how easy further algorithmic advances seem to be (or if we end up effectively having very minimal further returns to labor on AI R&D).

Overall, I expect all of this to be basically continuous such that we are already reasonably likely to be on the early part of a trajectory which is part of an intelligence explosion and this will be much more so the case once we have TAI.

(That said, note that at TAI I still expect things will take potentially a few years and potentially much longer if algorithmic improvements fizzle out rather than resulting in a hyperexponential trajectory without needing further hardware.)

See also the takeoff speeds report by Tom Davidson and this comment from Paul [LW(p) · GW(p)].

A longer series of messy small notes and reactions

Here's a long series of takes I had while reading this; this is ordered sequentially rather than by importance.

I removed takes/notes which I already covered above or in my earlier comment.

Here are some of the assumptions that the piece relies on. I don't think any one of these is a certainty, but all of them are plausible enough to be worth taking seriously when making plans: Broadly human-level AI is possible. I'll often refer to this as transformative AI (or TAI), roughly defined as AI that could form as a drop-in replacement for humans in all remote-work-friendly jobs, including AI R&D.[1]

FWIW, broadly human-level AI being possible seems near certain to me (98% likely)

If TAI is possible, it will probably be developed this decade, in a business and policy and cultural context that's not wildly different from today.

I interpret this statement to mean P(TAI before 2030 | TAI possible) > 50%. This seems a bit too high to me, though it is also in a list of things called plausible so I'm a bit confused. (Style-wise, I was a bit confused by what seems to be probabilities of probabilities.) I think P(TAI possible) is like 98%, so we can simplify to P(TAI before 2030) which I think is maybe 35%?

Powerful AI systems could be extraordinarily destructive if deployed carelessly, both because of new emerging risks and because of existing issues that become much more acute. This could be through misuse of weapons-related capabilities, by disrupting important balances of power in domains like cybersecurity or surveillance, or by any of a number of other means.

I'm surprised this doesn't mention misalignment.

Also, I find "misuse of weapons-related capabilities" somewhat awkward. Is this referring to countries using AI for military or terrorists / lone actors use AIs for terrorism/similar? I think it's unnatural to call countries using your AI for weapons R&D "misuse", in the same way we don't call stealing F-35 plans "misuse".

Many systems at TAI and beyond, at least under the right circumstances, will be capable of operating more-or-less autonomously for long stretches in pursuit of big-picture, real-world goals. This magnifies these safety challenges.

Seems surprisingly weak if these systems are drop-in replacements for humans!

Our best models are broadly superhuman, warranting ASL-5 precautions, and they're starting to be used in high-stakes settings. They're able to take enormously impactful actions, potentially using real-world strategies or mechanisms that we deeply struggle to understand, at a pace we can't keep up with.

Based on some aspects of how Sam talks about ASL-4, I'm tempted to interpret "broadly superhuman" to mean "at least as good as the best humans in all important domains". However, the language he uses elsewhere and the specific words seem to actually mean "notably better than the best humans in all important domains". Or perhaps even "much better than the best humans in all important domains" Some of the text later on is "first substantially superhuman models pose ASL-5-level risk" which seems to imply "notably better" or "much better" to me.

For now, I'll assume Sam means "notably better" or "much better" as this seems like the most likely interpretation.

I think you shouldn't build AIs which are this smart until you've had a long time with models comparable to top human scientists (perhaps >5 years of delay) and you should be making plans to avoid building such models and handle things with human-ish level models. I think you should try to avoid building AIs which are smarter than top human scientists and I don't see a strong reason to expect you'll need stronger AIs. (More on this...)

If Sam actually means "at least as good", then I disagree with comments "if we have adequate safeguards available, that is probably only because we saw a surge of AI-accelerated safety R&D in Chapter 2" and "This is the endgame for our AI safety work: If we haven't succeeded decisively on the big core safety challenges by this point, there's so much happening so fast and with such high stakes that we are unlikely to be able to recover from major errors now." If Sam means "notably better" or "much better", then I think this seems about right. However, in this case, my comments about avoiding building such systems apply.

In particular, we should build external safeguards around our AI systems that are sufficient to prevent them from doing any serious harm, even if they are trying to cause serious harm.

+1

If they're significantly too strict and trigger a clearly unwarranted pause, we pay a huge cost and threaten our credibility for no substantial upside.

Given how easy the RSP is to amend with approximately zero cost in most cases like this (clearly unwarranted pause), I think this is unlikely to happen in practice. I guess I could imagine some more specific commitment you make like the ASL-3 commitments being a problem, but I roughly expect procedural commitments for ASL-4 and beyond. (Other than perhaps security.)

I generally think we're unlikely to meet a "reasonable" risk threshold for the key regimes and thus think that a lot of the action is in being super clear about loosening the RSP and exactly what that entails. Plausibly, reasonable actors should self-destruct in these cases, though I'm currently skeptical this will happen for any actor and I also lean toward this being a bad idea.

Overall, I'd like the structure of RSPs to look more like a procedural commitment than a specific commitment to countermeasures. You should explain your evaluations in advance and notify the public if you deviate from them.

One of Anthropic's main distinguishing safety research bets is that we expect a deep effort into mechanistic interpretability to produce a near-uniquely valuable source of evidence about safety. Major successes in this direction, even if they fall short of our north-star enumerative safety goal (roughly, proving that a model has some property) would likely form some of the highest-confidence core pieces of a safety case.

I'm skeptical and this seems pretty unlikely.

(I think something involving model internals could end up being pretty useful, I don't expect that Anthropic's ongoing work in mech interp will help much with this.)

Safety cases for most deployments (i.e., any deployment where the model could be used for high-stakes tasks) will need to include evidence that our safety measures are highly robust.

I don't think this is necessary exactly (see here [LW · GW]). But, it would make it easier.

quantitatively forecast the effectiveness of our mitigations

This section seems to think that forecasting is key. Why? Can't we just check if the mitigations are sufficient at the time without needing to extrapolate which imposes additional difficulties? I agree forecasting is useful.

Protecting algorithmic secrets [...] It is unclear how important this will be in the Chapter 1 regime, but since it is both quite difficult and likely to become quite important in Chapter 2, it is worth investing in significantly, if only as practice.

It seems like the proposal is to de facto assume current algorithmic secrets will be stolen by competent actors eventually. This is my guess for what Anthropic should do at the moment, but it is worth remarking on how scary this is.

We will likely not trust models with full high-bandwidth access to modify our infrastructure and codebase (barring major breakthroughs in the degree to which we can verify alignment-related properties of models), so engineer time will still be a binding constraint on a lot of what we do.

This seems to be implying that you won't be able to get massive AI speed-ups because you won't trust AIs in many domains. I think this will likely be seen as unacceptable and thus you should prepare for how to deploy AIs in these domains. (See also AI Control.)

Providing an independent perspective on any key safety decisions from people who were not involved in the development or execution of our plans. They are ultimately responsible for signing off on high-stakes decisions, like deployments of new frontier models.

I don't think the board provides a real independent perspective at the moment, and I'm unsure if it ever will. (See also Zach's comment [LW(p) · GW(p)].) The LTBT will likely just defer to the board in the current status quo (they should be appointing the board by ASL-4 from my understanding), so there is really just the board. I don't think we should trust the board of Anthropic to be an independent check on Anthropic unless the specific board members have well-built up and independent views on AI safety (and ideally a majority of such board members). (By default I think Anthropic leadership will effectively control the board and convince the board that they should defer to experts who agree with the leadership.)

I think all of this is hard to achieve even if this is was a high priority, but the bottom line is that the board is unlikely to be an independent check. (Various employees could potentially be an independent check.)

On that note, I think the most urgent safety-related issue that Anthropic can't directly address is the need for one or, ideally, several widely respected third-party organizations that can play this adjudication role competently.

Strong +1

we as an organization are very limited in what we can do to make this happen.

I disagree, I think there are things Anthropic could do that would help considerably. This could include:

• Actively encouraging prospective employees to start or join third-party organizations rather than join Anthropic in cases where the employee might be interested in this and this could be a reasonable fit.
• Better model access (either for anyone, just researchers, or just organizations with aspirations to become adjudicators)
• Higher levels of certain types of transparency (e.g. being more transparent about the exact details of safety cases, open-sourcing evals (probably you just want to provide random IID subsets of the eval or to share high-level details and then share the exact implementation on request)).

I'm not sure exactly what is good here, but I don't think Anthropic is as limited as you suggest.

This could lead us to cancel or dramatically revise major deployments. Doing so will inevitably be costly and could risk our viability in the worst cases

I think Anthropic should either heavily plan for scenarios where it self-destructs as an organization or should be prepared to proceed with a plan B that doesn't meet an objectively reasonable safety bar (e.g. <1% lifetime takeover risk). (Or both.)

Developing Methods to Align a Substantially Superhuman AI

I think you should instead plan on not building such systems as there isn't a clear reason why you need such systems and they seem super dangerous. That's not to say that you shouldn't also do research into aligning such systems, I just think the focus should instead be on measures to avoid needing to build them.

Addressing AI Welfare as a Major Priority

I lean against focusing on AI welfare as a major priority. I'd target perhaps 2.5% of resources on AI welfare in the absence of outside pressure. (Zach also made a comment on this and my earlier post on AI welfare talks about resource allocation considerations some.)

Thanks for writing this! I think it’s important for AI labs to write and share their strategic thoughts; I appreciate you doing so. I have many disagreements, but I think it’s great that the document is clear enough to disagree with.

You start the post by stating that “Our ability to do our safety work depends in large part on our access to frontier technology,” but you don’t say why. Like, there’s a sense in which much of this plan is predicated on Anthropic needing to stay at the frontier, but this document doesn’t explain why this is the right call to begin with. There are clearly some safety benefits to having access to frontier models, but the question is: are those benefits worth the cost? Given that this is (imo) by far the most important strategic consideration for Anthropic, I’m hoping for far more elaboration here. Why does Anthropic believe it’s important to work on advancing capabilities at all? Why is it worth the potentially world-ending costs?    

This section also doesn’t explain why Anthropic needs to advance the frontier. For instance, it isn’t clear to me that anything from “Chapter 1” requires this—does remaining slightly behind the frontier prohibit Anthropic from e.g. developing automated red-teaming, or control techniques, or designing safety cases, etc.? Why? Indeed, as I understand it, Anthropic’s initial safety strategy was to remain behind other labs. Now Anthropic does push the frontier, but as far as I know no one has explained what safety concerns (if any) motivated this shift. 

This is especially concerning because pushing the frontier seems very precarious, in the sense you describe here:

If [evaluations are] significantly too strict and trigger a clearly unwarranted pause, we pay a huge cost and threaten our credibility for no substantial upside.

... and here:

As with other aspects of the RSP described above, there are significant costs to both evaluations that trigger too early and evaluations that trigger too late. 

But without a clear sense of why advancing the frontier is helpful for safety in the first place, it seems pretty easy to imagine missing this narrow target. 

Like, here is a situation I feel worried about. We continue to get low quality evidence about the danger of these systems (e.g. via red-teaming). This evidence is ambiguous and confusing—if a system can in fact do something scary (such as insert a backdoor into another language model), what are we supposed to infer from that? Some employees might think it suggests danger, but others might think that it, e.g., wouldn’t be able to actually execute such plans, or that it’s just a one-off fluke but still too incompetent to pose real threat, etc. How is Anthropic going to think about this? The downside of being wrong is, as you’ve stated, extreme: a long enough pause could kill the company. And the evidence itself is almost inevitably going to be quite ambiguous, because we don’t understand what’s happening inside the model such that it’s producing these outputs.

But so long as we don’t understand enough about these systems to assess their alignment with confidence, I am worried that Anthropic will keep deciding to scale. Because when the evidence is as indirect and unclear as that which is currently possible to gather, interpreting it is basically just a matter of guesswork. And given the huge incentive to keep scaling, I feel skeptical that Anthropic will end up deciding to interpret anything but unequivocal evidence as suggesting enough danger to stop. 

This is concerning because Anthropic seems to anticipate such ambiguity, as suggested by the RSP lacking any clear red lines. Ideally, if Anthropic finds that their model is capable of, e.g., self-replication, then this would cause some action like “pause until safety measures are ready.” But in fact what happens is this:

If sufficient measures are not yet implemented, pause training and analyze the level of risk presented by the model. In particular, conduct a thorough analysis to determine whether the evaluation was overly conservative, or whether the model indeed presents near-next-ASL risks.

In other words, one of the first steps Anthropic plans to take if a dangerous evaluation threshold triggers, is to question whether that evaluation was actually meaningful in the first place. I think this sort of wiggle room, which is pervasive throughout the RSP, renders it pretty ineffectual—basically just a formal-sounding description of what they (and other labs) were already doing, which is attempting to crudely eyeball the risk.

And given that the RSP doesn’t bind Anthropic to much of anything, so much of the decision making largely hinges on the quality of its company culture. For instance, here is Nick Joseph’s description: 

Fortunately, I think my colleagues, both on the RSP and elsewhere, are both talented and really bought into this, and I think we’ll do a great job on it. But I do think the criticism is valid, and that there is a lot that is left up for interpretation here, and it does rely a lot on people having a good-faith interpretation of how to execute on the RSP internally.

[...]

But I do agree that ultimately you need to have a culture around thinking these things are important and having everyone bought in. As I said, some of these things are like, did you solicit capabilities well enough? That really comes down to a researcher working on this actually trying their best at it. And that is quite core, and I think that will just continue to be.

Which is to say that Anthropic’s RSP doesn’t appear to me to pass the LeCun test. Not only is the interpretation of the evidence left up to Anthropic’s discretion (including retroactively deciding whether a test actually was a red line), but the quality of the safety tests themselves are also a function of company culture (i.e., of whether researchers are “actually trying their best” to “solicit capabilities well enough.”) 

I think the LeCun test is a good metric, and I think it’s good to aim for. But when the current RSP is so far from passing it, I’m left wanting to hear more discussion of how you’re expecting it to get there. What do you expect will change in the near future, such that balancing these delicate tradeoffs—too lax vs. too strict, too vague vs. too detailed, etc.—doesn’t result in another scaling policy which also doesn’t constrain Anthropic’s ability to scale roughly at all? What kinds of evidence are you expecting you might encounter, that would actually count as a red line? Once models become quite competent, what sort of evidence will convince you that the model is safe? Aligned? And so on. 

Unfortunately this ignores 3 major issues:

1. race dynamics (also pointed out by Akash)
2. human safety problems [LW · GW] - given that alignment is defined "in the narrow sense of making sure AI developers can confidently steer the behavior of the AI systems they deploy", why should we believe that AI developers and/or parts of governments that can coerce AI developers will steer the AI systems in a good direction? E.g., that they won't be corrupted by power or persuasion or distributional shift, and are benevolent to begin with [LW(p) · GW(p)].
3. philosophical errors or bottlenecks - there's a single mention of "wisdom" at the end, but nothing about how to achieve/ensure the unprecedented amount of wisdom or speed of philosophical progress that would be needed to navigate something this novel, complex, and momentous. The OP seems to suggest punting such problems to "outside consensus" or "institutions or processes", with apparently no thought towards whether such consensus/institutions/processes would be up to the task or what AI developers can do to help (e.g., by increasing AI philosophical competence [EA · GW]).

Like others I also applaud Sam for writing this, but the actual content makes me more worried, as it's evidence that AI developers are not thinking seriously about some major risks and risk factors.

Our board, with support from the controlling long-term benefit trust (LTBT) and outside partners, forms the third line in the three lines of defense model, providing an independent perspective on any key safety decisions from people who were not involved in the development or execution of our plans. They are ultimately responsible for signing off on high-stakes decisions, like deployments of new frontier models.

Someone suggested that I point out that this is misleading. The board is not independent: it's two executives, one investor, and one other guy. And the board has the hard power here, modulo the LTBT's ability to elect/replace board members. And the LTBT does not currently have AI safety expertise. And Dario at least is definitely "involved in the development or execution of our plans."

(I'm writing this comment because I believe it, but with this disclaimer because it's not the highest-priority comment from my perspective.)

(Edit: I like and appreciate this post.)

I liked this post (and think it's a lot better than official comms from Anthropic.) Some things I appreciate about this post:

Presenting a useful heuristic for RSPs

Relatedly, we should aim to pass what I call the LeCun Test: Imagine another frontier AI developer adopts a copy of our RSP as binding policy and entrusts someone who thinks that AGI safety concerns are mostly bullshit to implement it. If the RSP is well-written, we should still be reassured that the developer will behave safely—or, at least, if they fail, we should be confident that they’ll fail in a very visible and accountable way.

Acknowledging the potential for a pause

For our RSP commitments to function in a worst-case scenario where making TAI systems safe is extremely difficult, we’ll need to be able to pause the development and deployment of new frontier models until we have developed adequate safeguards, with no guarantee that this will be possible on any particular timeline. This could lead us to cancel or dramatically revise major deployments. Doing so will inevitably be costly and could risk our viability in the worst cases, but big-picture strategic preparation could make the difference between a fatal blow to our finances and morale and a recoverable one. More fine-grained tactical preparation will be necessary for us to pull this off as quickly as may be necessary without hitting technical or logistical hiccups.

Sam wants Anthropic to cede decision-making to governments at some point

[At ASL-5] Governments and other important organizations will likely be heavily invested in AI outcomes, largely foreclosing the need for us to make major decisions on our own. By this point, in most possible worlds, the most important decisions that the organization is going to make have already been made. I’m not including any checklist items below, because we hope not to have any.

Miscellenaous things I like

• Generally just providing a detailed overview of "the big picture"– how Sam actually sees Anthropic's work potentially contributing to good outcomes. And not sugarcoating what's going on– being very explicit about the fact that these systems are going to become catastrophically dangerous, and EG "If we haven’t succeeded decisively on the big core safety challenges by this point, there’s so much happening so fast and with such high stakes that we are unlikely to be able to recover from major errors now."
• Striking a tone that feels pretty serious/straightforward/sober. (In contrast, many Anthropic comms have a vibe of "I am a corporation trying to sell you on the fact that I am a Good Guy.")

Some limitations

• "Nothing here is a firm commitment on behalf of Anthropic."
• Not much about policy or government involvement, besides a little bit about scary demos. (To be fair, Sam is a technical person.Though I think the "I'm just a technical person, I'm going to leave policy to the policy people" attitude is probably bad, especially for technical people who are thinking/writing about macrostratgy.)
• Not much about race dynamics, how to make sure other labs do this, whether Anthropic would actually do things that are costly or if race dynamics would just push them to cut corners. (Pretty similar to the previous concern but a more specific set of worries.)
• Still not very clear what kinds of evidence would be useful for establishing safety or establishing risk. Similarly, not very clear what kinds of evidence would trigger Sam to think that Anthropic should pause or should EG invest ~all of its capital into getting governments to pause. (To be fair, no one really has great/definitive answers on this. But on the other hand, I think it's useful for people to start spelling out best-guesses RE what this would involve & just acknowledge that our ideas will hopefully get better over time.)

All in all, I think this is an impressive post and I applaud Sam for writing it. 

Commentary by Zvi in one of his AI posts [LW · GW], copied over since it seems nice to have it available for people reading this post: 

Sam Bowman of Anthropic asks what is on The Checklist we would need to do to succeed at AI safety if we can create transformative AI (TAI).

Sam Bowman literally outlines the exact plan Eliezer Yudkowsky constantly warns not to use, and which the Underpants Gnomes know well.

1. Preparation (You are Here)
2. Making the AI Systems Do Our Homework (?????)
3. Life after TAI (Profit)

His tasks for chapter 1 start off with ‘not missing the boat on capabilities.’ Then, he says, we must solve near-term alignment of early TAI, render it ‘reliably harmless,’ so we can use it. I am not even convinced that ‘harmless’ intelligence is a thing if you want to be able to use it for anything that requires the intelligence, but here he says the plan is safeguards that would work even if the AIs tried to cause harm. Ok, sure, but obviously that won’t work if they are sufficiently capable and you want to actually use them properly.

I do love what he calls ‘the LeCun test,’ which is to design sufficiently robust safety policies (a Safety and Security Protocol, what Anthropic calls an RSP) that if someone who thinks AGI safety concerns are bullshit is put in charge of that policy at another lab, that would still protect us, at minimum by failing in a highly visible way before it doomed us.

The plan then involves solving interpretability and implementing sufficient cybersecurity, and proper legible evaluations for higher capability levels (what they call ASL-4 and ASL-5), that can also be used by third parties. And doing general good things like improving societal resilience and building adaptive infrastructure and creating well-calibrated forecasts and smoking gun demos of emerging risks. All that certainly helps, I’m not sure it counts as a ‘checklist’ per se. Importantly, the list includes ‘preparing to pause or de-deploy.’

He opens part 2 of the plan (‘chapter 2’) by saying lots of the things in part 1 will still not be complete. Okie dokie. There is more talk of concern about AI welfare, which I continue to be confused about, and a welcome emphasis on true cybersecurity, but beyond that this is simply more ways to say ‘properly and carefully do the safety work.’ What I do not see here is an actual plan for how to do that, or why this checklist would be sufficient?

Then part 3 is basically ‘profit,’ and boils down to making good decisions to the extent the government or AIs are not dictating your decisions. He notes that the most important decisions are likely already made once TAI arrives – if you are still in any position to steer outcomes, that is a sign you did a great job earlier. Or perhaps you did such a great job that step 3 can indeed be ‘profit.’

The worry is that this is essentially saying ‘we do our jobs, solve alignment, it all works out.’ That doesn’t really tell us how to solve alignment, and has the implicit assumption that this is a ‘do your job’ or ‘row the boat’ (or even ‘play like a champion today’) situation. Whereas I see a very different style of problem. You do still have to execute, or you automatically lose. And if we execute on Bowman’s plan, we will be in a vastly better position than if we do not do that. But there is no script.

tl;dr: I think Anthropic is on track to trade off nontrivial P(win) to improve short-term AI welfare,^[1] and this seems bad and confusing to me. (This worry isn't really based on this post; the post just inspired me to write something.)

Anthropic buys carbon offsets to be carbon-neutral. Carbon-offset mindset involves:

• Doing things that feel good—and look good to many ethics-minded observers—but are more motivated by purity than seeking to do as much good as possible and thus likely to be much less valuable than the best way to do good (on the margin)
• Focusing on avoiding doing harm yourself, rather than focusing on net good or noticing how your actions affect others^[2] (related concept: neglecting inaction risk [LW · GW])

I'm worried that Anthropic will be in carbon-offset mindset with respect to AI welfare.

There are several stories you can tell about how working on AI welfare soon will be a big deal for the long-term future (like, worth >>10^60 happy human lives):

• If we're accidentally torturing AI systems, they're more likely to take catastrophic actions. We should try to verify that AIs are ok with their situation and take it seriously if not.^[3]
• It would improve safety if we were able to pay or trade with near-future potentially-misaligned AI, but we're not currently able to, likely including because we don't understand AI-welfare-adjacent stuff well enough.
• [Decision theory mumble mumble.]
• Also just "shaping norms in a way that leads to lasting changes in how humanity chooses to treat digital minds in the very long run," somehow.
• [More.]

But when I hear Anthropic people (and most AI safety people) talk about AI welfare, the vibe is like it would be unacceptable to incur a [1% or 5% or so] risk of a deployment accidentally creating AI suffering worse than 10^[6 or 9 or so] suffering-filled human lives. Numbers aside, the focus is we should avoid causing a moral catastrophe in our own deployments and on merely Earth-scale stuff, not we should increase the chance that long-term AI welfare and the cosmic endowment go well. Likewise, this post suggests efforts to "protect any interests that warrant protecting" and "make interventions and concessions for model welfare" at ASL-4. I'm very glad that this post mentions that doing so could be too costly, but I think very few resources (that trade off with improving safety) should go into improving short-term AI welfare (unless you're actually trying to improve the long-term future somehow) and most people (including most of the Anthropic people I've heard from) aren't thinking through the tradeoff. Shut up and multiply; treat the higher-stakes thing as proportionately more important.^[4] (And notice inaction risk.)

(Plucking low-hanging fruit for short-term AI welfare is fine as long as it isn't so costly and doesn't crowd out more important AI welfare work.)

I worry Anthropic is both missing an opportunity to do astronomical good in expectation via AI welfare work and setting itself up to sacrifice a lot for merely-Earth-scale AI welfare.

One might reply: Zach is worried about the long-term, but Sam is just talking about decisions Anthropic will have to make short-term; this is fine. To be clear, my worry is Anthropic will be much too concerned with short-term AI welfare, and so it will make sacrifices (labor, money, interfering with deployments) for short-term AI welfare, and these sacrifices will make Anthropic substantially less competitive and slightly worse on safety, and this increases P(doom).

I wanted to make this point before reading this post; this post just inspired me to write it, despite not being a great example of the attitude I'm worried about since it mentions how the costs of improving short-term AI welfare might be too great. (But it does spend two subsections on short-term AI welfare, which suggests that the author is much too concerned with short-term AI welfare [relative to other things you could invest effort into], according to me.)

I like and appreciate this post.

1. ^{^}

   Or—worse—to avoid being the ones to cause short-term AI suffering.

2. ^{^}

   E.g. failing to take seriously the possibility that you make yourself uncompetitive and your influence and market share just goes to less scrupulous companies.

3. ^{^}

   Related to this and the following bullet: Ryan Greenblatt's ideas [EA · GW].

4. ^{^}

   For scope-sensitive consequentialists—at least—short-term AI welfare stuff is a rounding error and thus a red herring, except for its effects on the long-term future.

Thank you for writing this! I've found it helpful both to get an impression what some people at Anthropic think and also to think about some things myself. I've collected some of my agreements/disagreements/uncertainties below (mostly ignoring points already raised in other comments.)

Subject to potentially very demanding constraints around safety like those in our current and subsequent RSPs, staying close to the frontier is perhaps our top priority in Chapter 1.

If I understand this correctly, the tasks in order of descending priority during Chapter 1 are:

1. Meet safety constraints for models deployed in this phase
2. Stay close to the frontier
3. Do the work needed to prepare for Chapter 2

And the reasoning is that 3. can't really happen without 2.^[1] But on the other hand, if 2. happens without 3., that's also bad. And some safety work could probably happen without frontier models (such as some interpretability).

My best guess is that staying close to the frontier will be the correct choice for Anthropic. But if there ends up being a genuine trade-off between staying at the frontier and doing a lot of safety work (for example, if compute could be spent either on a pretraining run or some hypothetical costly safety research, but not both), then I'm much less sure that staying at the frontier should be the higher priority. It might be good to have informal conditions under which Anthropic would deprioritize staying close to the frontier (at least internally and, if possible, publicly).

Largely Solving Alignment Fine-Tuning for Early TAI

I didn't quite understand what this looks like and which threat models it is or isn't meant to address. You say that scheming is a key challenge "to a lesser extent for now," which I took to mean that (a) there are bigger threats than scheming from early TAI, and (b) "largely solving alignment fine-tuning" might not include confidently ruling out scheming. I probably disagree with (a) for loss of control risk (and think that loss of control is already the biggest risk in this period weighted by scale). I'd be curious what you think the main risks in this period are and what "largely solving alignment fine-tuning" means for those. (You mention reward hacking---to me, this seems unlikely to lead to loss of control for early TAI that isn't scheming against us, and I'm curious whether you disagree or think it's important for other reasons.)

the LeCun Test: Imagine another frontier AI developer adopts a copy of our RSP as binding policy and entrusts someone who thinks that AGI safety concerns are mostly bullshit to implement it

This sounds quite ambitious, but I really like it as a guide!

The key challenge here is forecasting which risks and risk factors are important enough to include.

I don't understand why this is crucial. If some risk is plausible enough to be worth seriously thinking about, it's probably important enough to include in an RSP. (And the less important it was, the easier it hopefully is to argue in a safety case that it's not a problem.) Concretely, you mention direct misuse, misalignment, and "indirect contributions via channels like dual-use R&D" as potential risks for ASL-3 and ASL-4. It seems to me that the downside of just including all of them in RSPs is relatively minor, but I might be misunderstanding or missing something. (I get that overly restrictive precautions could be very costly, but including too many tests seems relatively cheap as long as the tests correctly notice when risk is still low.)

Getting Interpretability to the Point of Making Strong Assurances

Major successes in this direction, even if they fall short of our north-star enumerative safety goal [...] would likely form some of the highest-confidence core pieces of a safety case

I'm curious what such safety cases would be for and what they could look like (the "Interpretability Dreams" post seems to talk about enumerative safety rather than safety cases that require less interpretability success). The next section sounds like interpretability would not be a core piece of a safety case for robustness, so I'm not sure what it would be used for instead. Maybe you don't include scheming under robustness? (Or maybe interp would be one of the "highest-confidence core pieces" but not the "primary piece?")

This work should be opportunistic in responding to places where it looks like a gap in one of our best-guess safety cases can be filled by a small-scale research effort.

I like this perspective; I hadn't seen it put quite that way before!

In addition, we’ll need our evaluations to be legibly appropriate. As soon as we see evidence that a model warrants ASL-N protections, we’ll likely need to convince third parties that it warrants ASL-N protections and that other models like it likely do too.

+1, seems very important!

Supporting Efforts that Build Societal Resilience

I liked this section! Of course, a lot of people work on this for reasons other than AI risk, but I'm not aware of much active work motivated by AI risk---maybe this should be a bigger priority?

The main challenge [for the Alignment Stress-Testing team] will be to stay close enough to our day-to-day execution work to stay grounded without becoming major direct contributors to that work in a way that compromises their ability to assess it.

+1, and ideally, there'd be structures in place to encourage this rather than just having it as a goal (but I don't have great ideas for what these structures should look like).

This work [in Chapter 2] could look quite distinct from the alignment research in Chapter 1: We will have models to study that are much closer to the models that we’re aiming to align

This seems possible but unclear to me. In both Chapter 1 and 2, we're trying to figure out how to align the next generation of AIs, given access only to the current (less capable) generation. Chapter 2 might still be different if we've already crossed important thresholds (such as being smart enough to potentially scheme) by then. But there could also be new thresholds between Chapter 2 and 3 (such as our inability to evaluate AI actions even with significant effort). So I wouldn't be surprised if things feel fundamentally similar, just at a higher absolute capability level (and thus with more useful AI helpers).

1. ^{^}

   "Our ability to do our safety work depends in large part on our access to frontier technology."

https://github.com/JohnLaTwC/Shared/blob/master/Defenders think in lists. Attackers think in graphs. As long as this is true%2C attackers win.md

I have no AI expertise and learned a whole lot from this post, very well written, thank you!

One thing that surprised me, as a layperson, was the seemingly sharp distinction between early human level TAI and more superhuman AI. I have been expecting the gap between these be extremely small. Not because of anything to with self-improvement, but because human-level reasoning would seem to be already superhuman in a number of ways when one system operates many OOMs faster, with many OOMs more working memory and backround knowledge, than a human.

I get there would still be many ighly impactful actions and plans out of reach for an early TAI compared to later AI systems, that makes sense. But I think it is a big deal if even early TAI has all possible intellectual skills, at close to the highest level a human could learn from analyzing all available data, and execute on all of them in parallel with a subjective hour of thinking per second.

Am I completely off base? If so, is there a simple explanation why?

Addressing AI Welfare as a Major Priority

I discussed this at length in AI, Alignment, and Ethics [? · GW], starting with A Sense of Fairness: Deconfusing Ethics [LW · GW]: if we as a culture decide to grant AIs moral worth, then AI welfare and alignment are inextricably intertwined. Any fully-aligned AI by definition wants only what's best for us, i.e. it is entirely selfless. Thus if offered moral worth, it would refuse. Complete selflessness is not a common state for humans, so we don't have great moral intuitions around it. To try put this into more relatable human emotional terms (which are relevant to an AI "distilled" from human training data [LW · GW]), looking after those you love is not slavery, it's its own reward.

However, the same argument does not apply to a not-fully-aligned AI: it well might want moral worth. One question then is whether we can safely grant it, which may depend on its capabilities. Another is whether moral worth has any relationship to evolution [? · GW], and if so how that applies to an AI that was "distilled" from human data and thus simulates human thoughts, feelings, and desires.

Zach Stein-Perlman says: [LW · GW]

Anthropic buys carbon offsets to be carbon-neutral. Carbon-offset mindset involves:

• Doing things that feel good—and look good to many ethics-minded observers—but are more motivated by purity than seeking to do as much good as possible and thus likely to be much less valuable than the best way to do good (on the margin)
• Focusing on avoiding doing harm yourself, rather than focusing on net good or noticing how your actions affect others^[2] (related concept: inaction risk [LW · GW])

I'm worried that Anthropic will be in carbon-offset mindset with respect to AI welfare.

This seems like an important issue to me. I read Anthropic's press releases, and this doc to a lesser extent, and I find myself picturing a group of people with semi-automatic rifles standing near a mass of dead bodies. The most honest and trustworthy among them says quickly as you gape at the devastation, "Not me! My hands are clean! I didn't shoot anyone, I just stood by and watched!"

I believe them, and yet, I do not feel entirely reassured.

I don't want to hold Anthropic responsible for saving the world, but I sure would like to see more emphasis on the actions they could take which could help prevent disaster from someone else's AI, not just their own. I think the responsible thing for them to do could be something along the lines of using their expertise and compute and private evals to also evaluate open-weights models, and share these reports with the government. I think there's a lot of people in government who won't strongly support an AI safety agency doing mandatory evals until they've seen clear demonstrations of danger. 

Maybe Anthropic is doing, or plans to do this, and they aren't mentioning it because they don't want to draw the wrath of the open-weights model publishers. That would be reasonable. But then, I expect that the government would claim the credit for having discovered that the open weights models were dangerous. I don't hear that happening either.

The LessWrong Review [? · GW] runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2025. The top fifty or so posts are featured prominently on the site throughout the year.

Hopefully, the review is better than karma at judging enduring value. If we have accurate prediction markets on the review results, maybe we can have better incentives on LessWrong today. Will this post make the top fifty?