On: So I guess everyone uses LLMs to think now

[strangecasts]

It matters for monitorability and debugging, viz. OpenAI's misalignment reports which quote heavily from the CoT https://alignment.openai.com/misalignment-reports/

[CamperBob2 → strangecasts]

Sounds like somebody else's problem to me. When I want to see the chain of thought, I use a local model. It's seldom enlightening.

[strangecasts → CamperBob2]

Okay, well, I can't force you to give a shit, I'm saying whether CoT is deceptive is a pretty important question if major AI labs are making monitoring of it a core safety premise https://web.stanford.edu/~cgpotts/blog/cot/#deceptive