Why would you assume that the same capability could not be used to harden system... | Hacker News

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

fooker 19 days ago | parent | context | favorite | on: Our position on open-weights models

Why would you assume that the same capability could not be used to harden systems?

igor47 19 days ago [–]

Addressed in the source, but there's an asymmetry favoring the attackers. They only have to find one exploit once. The defenders have to be perfect all the time.

fooker 19 days ago | [–]

How's that asymmettry worse than it is now?

itemize123 19 days ago | | [–]

quite simply because models become better?

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