That’s a good explanation for the behavior. It is sad that the natural direction... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		bugbuddy 6 months ago \| parent \| context \| favorite \| on: Chain of thought monitorability: A new and fragile... That’s a good explanation for the behavior. It is sad that the natural direction of the competition drives the products to be less transparent. That is a win for open-weight models.

OutOfHere 6 months ago [–]

To add clarity, it's a win for open-weight models precisely because only their CoT can be analyzed by the user for task-specific alignment.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact