wh
@nrehiew_
eng primarily, ml mostly, research previously
参加 October 2023
104 フォロー中 18.5K ファン
It looks like all it took to bypass Opus's guardrails was to make it think it was attempting a CTF during a /goal
They used Opus 5 to pull off the hack. It appears they had access to the loosened cyber-guardrail version of Opus. They successfully accessed the OAI internal monorepo. The question that will be asked is, if these three guys can pull this off, what can a nation state do.
もっと見る
