Thanks - I see, I was misunderstanding. 

Proposal part 1: Shoggoth/Face Distinction: Instead of having one model undergo agency training, we have two copies of the base model work together, specializing in different parts of the job, and undergo training together. Specifically we have the "shoggoth" copy responsible for generating all the 'reasoning' or 'internal' CoT, and then we have the "face" copy responsible for the 'actions' or 'external' outputs. So e.g. in a conversation with the user, the Shoggoth would see the prompt and output a bunch of reasoning token CoT; the Face would see the prompt + all that CoT and then output a message to pass to the user, and then the process would repeat.

Proposal part 2: Blind the Evaluation Process to the Internal Reasoning: Remember that reward process that evaluates overall performance? Hide from it all the outputs of the Shoggoth. Just show it the outputs from the Face. 

I don't see how this proposal could get you AGI-level capabilities. You need the "shoggoth" part of the model to gain general purpose capabilities somehow, and if you are completely shielding the shoggoth from RL, all of the capabilities have to come from pre-training, which seems unlikely. My guess is that a more realistic proposal involves having separate reward models for the two parts: 

1. The shoggoth RM, which only rewards capabilities
2. The face RM, which also includes alignment-relevant stuff 

But it isn't clear to me how to separate out the alignment/capabilities. IIUC the hope is that the capabilities training seems would naturally incentivize the shoggoth to have bad goals, and perhaps instrumentally decieve the humans, but to do this deception in the COT in english so we can see. 

You later write: 

How it all (hopefully) fits together: First, because of the paraphraser, the Shoggoth will not learn to speak in some optimized alien language, or even to speak in jargon or euphemisms -- because semantics not recognized by the paraphraser will be scrambled by it. So the Shoggoth will continue to 'think in English' even as it undergoes lots of agency training and learns substantial new skills.

Second, because the training process is blind to the outputs of the Shoggoth (and instead only sees what the Face outputs), there should be no pressure on the Shoggoth to learn to decieve, conceal, dissemble, doublethink, etc. Instead the Shoggoth will be 'free' to put all its important thoughts in plain English.

Which suggests we are training the shoggoth with agency training. But I don't understand how this is consistnet with "the training process be blind to the outputs of the Shoggoth". Did you mean just some "alignment" subset of the training process? 

I think a problem with all the proposed terms is that they are all binaries, and one bit of information is far too little to characterize takeoff: 

• One person's "slow" is >10 years, another's is >6 months. 
• The beginning and end points are super unclear; some people might want to put the end point near the limits of intelligence, some people might want to put the beginning points at >2x AI R&D speed, some at 10, etc. 
• In general, a good description of takeoff should characterize capabilities at each point on the curve.  

So I don't really think that any of the binaries are all that useful for thinking or communicating about takeoff. I don't have a great ontology for thinking about takeoff myself to suggest instead, but I generally try to in communication just define a start and end point and then say quantitatively how long this might take. One of the central ones I really care about is the time between wakeup and takeover capable AIs. 

wakeup = "the first period in time when AIs are sufficiently capable that senior government people wake up to incoming AGI and ASI" 

takeover capable AIs = "the first time there is a set of AI systems that are coordinating together and could take over the world if they wanted to" 

The reason to think about this period is that (kind of by construction) it's the time where unprecedented government actions that matter could happen. And so when planning for that sort of thing this length of time really matters. 

Of course, the start and end times I think about are both fairly vague. They also aren't purely a function of AI capabilities, and they care about stuff like "who is in government" and "how capable our institutions are at fighting a rogue AGI".  Also, many people believe that we never will get takeover capable AIs even at superintelligence.

Perhaps that was overstated. I think there is maybe a 2-5% chance that Anthropic directly causes an existential catastrophe (e.g. by building a misaligned AGI). Some reasoning for that: 

1. I doubt Anthropic will continue to be in the lead because they are behind OAI/GDM in capital. They do seem around the frontier of AI models now, though, which might translate to increased returns, but it seems like they do best on very short timelines worlds. 
2. I think that if they could cause an intelligence explosion, it is more likely than not that they would pause for at least long enough to allow other labs into the lead. This is especially true in short timelines worlds because the gap between labs is smaller. 
3. I think they have much better AGI safety culture than other labs (though still far from perfect), which will probably result in better adherence to voluntary commitments.  
4. On the other hand, they haven't been very transparent, and we haven't seen their ASL-4 commitments. So these commitments might amount to nothing, or Anthropic might just walk them back at a critical juncture. 

2-5% is still wildly high in an absolute sense! However, risk from other labs seems even higher to me, and I think that Anthropic could reduce this risk by advocating for reasonable regulations (e.g. transparency into frontier AI projects so no one can build ASI without the government noticing). 

I agree with Zach that Anthropic is the best frontier lab on safety, and I feel not very worried about Anthropic causing an AI related catastrophe. So I think the most important asks for Anthropic to make the world better are on its policy and comms. 

I think that Anthropic should more clearly state its beliefs about AGI, especially in its work on policy. For example, the SB-1047 letter they wrote states: 

Broad pre-harm enforcement. The current bill requires AI companies to design and implement SSPs that meet certain standards – for example they must include testing sufficient to provide a "reasonable assurance" that the AI system will not cause a catastrophe, and must "consider" yet-to-be-written guidance from state agencies. To enforce these standards, the state can sue AI companies for large penalties, even if no actual harm has occurred. While this approach might make sense in a more mature industry where best practices are known, AI safety is a nascent field where best practices are the subject of original scientific research. For example, despite a substantial effort from leaders in our company, including our CEO, to draft and refine Anthropic's RSP over a number of months, applying it to our first product launch uncovered many ambiguities. Our RSP was also the first such policy in the industry, and it is less than a year old. What is needed in such a new environment is iteration and experimentation, not prescriptive enforcement. There is a substantial risk that the bill and state agencies will simply be wrong about what is actually effective in preventing catastrophic risk, leading to ineffective and/or burdensome compliance requirements.

Liability doesn’t not address the central threat model of AI takeover, for which pre-harm mitigations are necessary due to the irreversible nature of the harm. I think that this letter should have acknowledged that explicitly, and that not doing so is misleading. I feel that Anthropic is trying to play a game of courting political favor by not being very straightforward about its beliefs around AGI, and that this is bad. 

To be clear, I think it is reasonable that they argue that the FMD and government in general will be bad at implementing safety guidelines while still thinking that AGI will soon be transformative. I just really think they should be much clearer about the latter belief. 

The fact that AIs will be able to coordinate well with each other, and thereby choose to "merge" into a single agent

My response: I agree AIs will be able to coordinate with each other, but "ability to coordinate" seems like a continuous variable that we will apply pressure to incrementally, not something that we should expect to be roughly infinite right at the start. Current AIs are not able to "merge" with each other.

Ability to coordinate being continuous doesn't preclude sufficiently advanced AIs acting like a single agent. Why would it need to be infinite right at the start? 

And of course current AIs being bad at coordination is true, but this doesn't mean that future AIs won't be.  
 

Thanks for the response! 

If instead of reward circuitry inducing human values, evolution directly selected over policies, I'd expect similar inner alignment failures.

I very strongly disagree with this. "Evolution directly selecting over policies" in an ML context would be equivalent to iterated random search, which is essentially a zeroth-order approximation to gradient descent. Under certain simplifying assumptions, they are actually equivalent. It's the loss landscape an parameter-function map that are responsible for most of a learning process's inductive biases (especially for large amounts of data). See: Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent. 

I think I understand these points, and I don't see how this contradicts what I'm saying. I'll try rewording. 

Consider the following gaussian process: 

Each blue line represents a possible fit of the training data (the red points), and so which one of these is selected by a learning process is a question of inductive bias. I don't have a formalization, but I claim: if your data-distribution is sufficiently complicated, by default, OOD generalization will be poor. 

Now, you might ask, how is this consistent with capabilities to generalizing? I note that they haven't generalized all that well so far, but once they do, it will be because the learned algorithm has found exploitable patterns in the world and methods of reasoning that generalize far OOD. 

You've argued that there are different parameter-function maps, so evolution and NNs will generalize differently, this is of course true, but I think its besides the point. My claim is that doing selection over a dataset with sufficiently many proxies that fail OOD without a particularly benign inductive bias leads (with high probability) to the selection of function that fails OOD. Since most generalizations are bad, we should expect that we get bad behavior from NN behavior as well as evolution. I continue to think evolution is valid evidence for this claim, and the specific inductive bias isn't load bearing on this point -- the related load bearing assumption is the lack of a an inductive bias that is benign. 

If we had reasons to think that NNs were particularly benign and that once NNs became sufficiently capable, their alignment would also generalize correctly, then you could make an argument that we don't have to worry about this, but as yet, I don't see a reason to think that a NN parameter function map is more likely to lead to inductive biases that pick a good generalization by default than any other set of inductive biases. 

It feels to me as if your argument is that we understand neither evolution nor NN inductive biases, and so we can't make strong predictions about OOD generalization, so we are left with our high uncertainty prior over all of the possible proxies that we could find. It seems to me that we are far from being able to argue things like "because of inductive bias from the NN architecture, we'll get non-deceptive AIs, even if there is a deceptive basin in the loss landscape that could get higher reward." 

I suspect you think bad misgeneralization happens only when you have a two layer selection process (and this is especially sharp when there's a large time disparity between these processes), like evolution setting up the human within lifetime learning. I don't see why you think that these types of functions would be more likely to misgeneralize. 

(only responding to the first part of your comment now, may add on additional content later) 

We haven't asked specific individuals if they're comfortable being named publicly yet, but if advisors are comfortable being named, I'll announce that soon. We're also in the process of having conversations with academics, AI ethics folks,  AI developers at small companies, and other civil society groups to discuss policy ideas with them.

So far, I'm confident that our proposals will not impede the vast majority of AI developers, but if we end up receiving feedback that this isn't true, we'll either rethink our proposals or remove this claim from our advocacy efforts.  Also, as stated in a comment below:

I’ve changed the wording to “Only a few technical labs (OpenAI, DeepMind, Meta, etc) and people working with their models would be regulated currently.” The point of this sentence is to emphasize that this definition still wouldn’t apply to the vast majority of AI development -- most AI development uses small systems, e.g. image classifiers, self driving cars, audio models, weather forecasting, the majority of AI used in health care, etc.