Good post.  I agree with the headline that faithful CoT is a promising path forward for interpreting and supervising LLMs. 

TL;DR: I'd suggest researchers focus more narrowly on a subset of unfaithful chain-of-thought: steganographic/encoded reasoning that the model is using to perform hidden serial reasoning, as studied in Roger et al. IMO this type of unfaithfulness is more important, more neglected, and more tractable to fix than the sort of post-hoc reasoning studied in Turpin et al., or the hidden parallel reasoning studied in Pfau et al.

I think it's worth distinguishing between three kinds of unfaithful chain of thought that can occur when you ask a model a question and give it time to  (I'm slightly adapting this trichotomy from Lanham et al.):

• Epiphenomenal (typically post-hoc) reasoning: This is when the process of writing a CoT explanation is not actually helping the model produce its answer.  This can be okay, if (as OP mentions), the model is just accurately explaining the reasoning process that it followed to produce its answer.  But it can also lead to explanations that are inaccurate, as Turpin et al. demonstrate; these explanations leave out important reasons for a decision and/or make false predictions about how the model would behave on other inputs.  For more on whether models' explanations make accurate predictions about their counterfactual behaviors, see here.
• Hidden parallelized reasoning: This is when a model does a bunch of reasoning while generating a chain of thought, but it doesn't encode any of its intermediate calculations/conclusions in the tokens it produces. It just uses the fact that it has lots of tokens to think with to do a large number of parallelized calculations. See Pfau et al. for a demonstration of what this looks like; you can make models that get a question wrong if forced to answer immediately, but get it right if you ask them "[Question]?...........................Give your answer now:". 
  • Something like hidden parallelized reasoning may emerge naturally from pre-training,  as studied in Wu et al. They show that larger models do more "pre-caching", i.e. computing a feature that is useless for predicting the literal next token, but will be useful for predicting some future next token down the line.
• Steganography/encoded serial reasoning:  This is when a model uses the words it generates in its chain of thought to accomplish as task that it could not do in a single forward pass, but it encodes meaning in its word choice that is opaque to a typical overseer. This is demonstrated in Roger et al., which takes a model that is too dumb to learn a QA task without CoT but can learn the task with CoT, and then teaches it to perform the task using steganographic CoTs.

I think steganography is the most concerning form of unfaithful chain-of-thought of these three, but it's also the easiest to study and mitigate. That is to say, I think it's more important, more neglected, and more tractable than the other two.

• Importance/scariness of steg vs. other forms of unfaithfulness: I think steganographic reasoning in chains of thought is both reasonably likely to emerge naturally and potentially quite dangerous, especially compared to epiphenomenal and hidden parallelized reasoning.
  • Why likely? It seems useful for multi-step reasoning to arbitrarily assign information-laden connotations to pairs of words that are synonymous to humans, especially under a financial pressure to use reduce the number of tokens used.  Also, OpenAI performed no public tests for steganography on o1 and this OpenAI RS says he'd be totally happy with steganography, so I get the sense that OpenAI at least isn't prioritizing avoiding steg highly.
  • Why dangerous? Steganographic CoTs allow models to perform long chains of serial reasoning outside human oversight, and to send messages to other AIs (esp. copies of themselves). 
    • This could allow models to:
      • Generate complex plans for escaping safety measures and going rogue.
      • Carefully analyze their inputs to distinguish real chances to defect from synthetic honeypots, or distinguish insecure containment environments (that could be escaped from) from secure ones.
      • Subtly collude with other copies of themselves in order to coordinate on e.g. sabotaging AI developers' cybersecurity, alignment research, or AI training code.
  • Meanwhile, epiphenomenal and hidden parallelized reasoning don't allow for very long and complex trains of thought, or for hidden communication with other AIs. 
• Neglectedness: Almost all work on CoT faithfulness (e.g. this) focuses entirely on unfaithful post-hoc reasoning and ignores steganography entirely. I conjecture that this is because long, RL-trained CoTs are new with o1, and there hasn't been clear evidence of steganographic reasoning occurring organically yet. That said, I'd guess o1 is already steganographic, on this basis of this sort of thing. 
• Tractability: Roger et al. find that "paraphrasing is an effective defense against all steganography schemes we’ve tried" and Radhakrishnan et al. find that "Question Decomposition Improves the Faithfulness of Model-Generated Reasoning". I am pretty skeptical that these basic defenses can resist optimization pressures against them, and I'd bet that further research will overturn Roger et al.'s blue-team victory. But I'd like to see the SOTA on defenses pushed further; I think that defenses can probably reduce steganography somewhat and make it incrementally harder for future AIs to defect.

I think there are a lot of exciting follow-up directions for future research here; finding cases where steg emerges organically, testing out different paraphrasing approaches for reducing steg, finding ways of decomposing tasks into subproblems to reduce how much context/background info any given copy of a model has (and then preventing the copies from steganographically communicating).

(I'd be interested in hearing about any good work in this area that I haven't mentioned in this comment, if anyone is aware of some)

I got a bit lost in understanding your exit plan. You write

My preferred exit plan is to build human-obsoleting AIs which are sufficiently aligned/trustworthy that we can safely defer to them 

Some questions about this and the text that comes after it:

1. How do you achieve such alignment? You wrote that you worry about the proposal of perfectly + scalably solving alignment, but I worry about how to achieve even the imperfect alignment of human-ish-level AIs that you're describing here. What techniques are you imagining using?
2. Why do these AIs need to be human-obsoleting? Why not just human-accelerating?
3. Why does your exit plan involve using powerful and aligned AIs to prepare for superintelligence, rather than merely using controlled AIs of that capability level? Do you think that it would be hard/dangerous to try to control "human-obsoleting" AIs?
4. Why do you "expect that ruling out egregious misalignment is the hardest part in practice"? That seems pretty counterintuitive to me. It's easy to imagine descendants of today's models that don't do anything egregious but have pretty different values from me and/or the general public; these AIs wouldn't be "philosophically competent".
5. What are you buying time to do? I don't understand how you're proposing spending the "3 years of time prior to needing to build substantially superhuman AIs". Is it on alignment for those superhuman AIs? 
6. You mention having 3 years, but then you say "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." I found this confusing.
7. What do you mean by "a high fraction of risk comes from building wildly superhuman AI and it seems much easier to mitigate risks prior to this point." It seems easier to mitigate which risks prior to what point? And why? I didn't follow this.

Thanks, edited my post to reference this (lmk if you understand what's happening here better than I do)

Thanks, this is a helpful comment. Fixed the typo

Edit: The sitation has evolved but is still somewhat confusing. There is now a leaderboard of scores on the public test set that Ryan is #1 on (see here). But this tweet from Jack Cole indicates that his (many month old) solution gets a higher score on the public test set than Ryan's top score on that leaderboard. I'm not really sure what's going on here,

•  Why isn't Jack's solution on the public leaderboard?
• Is the semi-pubic test set the same as the old private set?
• If not, is it equal in difficulty to the public test set, or the harder private test set?
• Here it says "New high scores are accepted when the semi-private and public evaluation sets are in good agreement". What does that mean?

One important caveat to the presentation of results in this post (and the discussion on Twitter) is that there are reasons to think this approach may not be SOTA, as it performs similarly to the prior best-performing approach when tested apples-to-apples, i.e. on the same problems.

There are three sets of ARC problems: the public training set, the public eval set, and the private eval set. 

• Buck and Ryan got 71% on the first, 51% on the second, and [we don't know] on the third. 
• The past SOTA got [we don't know] on the first, 52% on the second, and 34% on the third.
• Humans get 85% on the first, [we don't know] on the second, and [we don't know] on the third

My two main deductions from this are:

• It's very misleading to compare human perf on the train set and AI perf on either of the test sets; the test sets seem way harder! Note that 71% is approaching 85%, so it seems like AIs are not far from human perf when you compare apples-to-apples. So graphs from the ARC folks like the one showing little progress towards human-level perf on this page are not scientifically valid.
• Buck and Ryan's approach doesn't exceed the past AI SOTA on the only apples-to-apples comparison we have so far. Unclear if it will beat it on the private test set. 

Apparently, lots of people get better performance on the public test set than the private one, which is a little surprising given that if you read this page from the ARC folks, you'll see the following:

The public training set is significantly easier than the others (public evaluation and private evaluation set) since it contains many "curriculum" type tasks intended to demonstrate Core Knowledge systems. It's like a tutorial level.

The public evaluation sets and the private test sets are intended to be the same difficulty.

Two explanations come to mind: maybe the public and private test sets are not IID, and/or maybe past SOTA method overfit to the public set. Chollet claims it's (accidentally) the latter here, but he doesn't rule out the former. He says the tasks across the two public test sets are meant to be equally hard for a human, but he doesn't say they're divided in an IID manner.

I guess we'll see how the results on the public leaderboard shake out.

(Expanding on a tweet)

"Follow the right people on twitter" is probably the best option. People will often post twitter threads explaining new papers they put out. There's also stuff like:

• News put together by CAIS: https://newsletter.mlsafety.org/ and https://newsletter.safe.ai/ and https://twitter.com/topofmlsafety
• News put together by Daniel Paleka: https://newsletter.danielpaleka.com/ and twitter summaries like https://twitter.com/dpaleka/status/1664617835178631170

I appreciate you transcribing these interviews William!

Did/will this happen?