"...We recommend against applying strong optimization pressure directly to the CoTs of frontier reasoning models, leaving CoTs unrestricted for monitoring."
https://openai.com/index/chain-of-thought-monitoring/
"...We recommend against applying strong optimization pressure directly to the CoTs of frontier reasoning models, leaving CoTs unrestricted for monitoring."
https://openai.com/index/chain-of-thought-monitoring/
https://gist.github.com/GideonPotok/9d8de616ee20571d1d38ea760c5b99a2
No comments:
Post a Comment