Anthropic themselves briefly discuss “illegible” CoT in the Mythos & Fable system card; the example they provide is on page 108 and has also been discussed on LW
Perfect, thanks, just what I was looking for.
This Twitter user is known for having an undisclosed method for accessing the CoT of OpenAI models. He sometimes posts snippets. Recent examples.
Anthropic themselves briefly discuss “illegible” CoT in the Mythos & Fable system card; the example they provide is on page 108 and has also been discussed on LW
Perfect, thanks, just what I was looking for.
This Twitter user is known for having an undisclosed method for accessing the CoT of OpenAI models. He sometimes posts snippets. Recent examples.