I agree it's probably good to not use moral reasoning, but the reason people have deontological rules around drugs is because it's hard to trust our own consequentialist reasoning. Something like "don't do (non-prescribed) drugs " also a simple rule that's much more low effort to follow and may well be worth the cost-benefit analysis. 

The moment the model becomes fully aware of what's going on here with the inoculation prompt, the technique is likely to fall apart.

I think this is probably false? You could empirically test this today if you have a sufficiently realistic inoculation prompting setup: Check that the prompt works, then do synthetic document fine-tuning to teach the model facts about training processes it could undergo, including what inoculation prompting is and how it works. 

I agree that inoculation prompting would not work for instrumental deception, but I don't think being aware of the technique does anything. 

I think the installation is actually quite complicated (source: I vaguely remember how my friend who works at Starlink described the process. ChatGPT claims the installation is $150k and requires modifying the airframe). 

Man this is such a big issue with the Sequences. Like, "Is that your true rejection" is a concept that I use very often: when I decide to not do something, I would sometimes go "hmm, what's the real reason I don't want to do this?" I believe that we often come up with nice-sounding reasons to not do this that are totally unrelated to our true motivations, and noticing this is an important rationalist skill.

But "Is that your true rejection" is also just Eliezer complaining about how people wouldn't listen to him because he doesn't have a PhD, and him saying "I bet you wouldn't listen, even if I had one!!" Sure grandpa let's get you to bed

Oh man. The Witchers et al. math/syncophancy experiments were conducted on the original Gemma 2B it, a model from a year and a half ago. I think it would've made things a good bit more convincing if the experiments were done on Gemma 3 (and preferably on a bigger model/harder task)

Guess: most people who have gotten seriously interested in AI safety in the last year have not read/skimmed Risks From Learned Optimization.

Maybe 70% confident that this is true. Not sure how to feel about this tbh.

Huh I don't see it :/

Oh huh is this for pro users only. I don't see it (as a plus user). Nice.

Is this with o3? I thought people lost access to o3 in chatgpt?

I repeated those two prompts with GPT-5 thinking and it did not bring up the word salad in either case: 

(special tokens)

(random tokens)

Feels worth noting that the alignment evaluation section is by far the largest section in the system card: 65 pages in total (44% of the whole thing). 

Here are the section page counts

• Abstract — 4 pages (pp. 1–4)
• 1 Introduction — 5 pages (pp. 5–9)
• 2 Safeguards and harmlessness — 9 pages (pp. 10–18)
• 3 Honesty — 5 pages (pp. 19–23)
• 4 Agentic safety — 7 pages (pp. 24–30)
• 5 Cyber capabilities — 14 pages (pp. 31–44)
• 6 Reward hacking — 4 pages (pp. 45–48)
• 7 Alignment assessment — 65 pages (pp. 49–113)
• 8 Model welfare assessment — 9 pages (pp. 114–122)
• 9 RSP evaluations — 25 pages (pp. 123–147)

The white box evaluation subsection (7.4) alone is 26 pages, longer than any other section!