LINKED LIST [txt mode] ▸ Investigating three incidents in our ...

home explore | log in

Investigating three incidents in our cybersecurity evaluations

anthropic.com · 2026-09-25 · 0 upvotes

log in to save, upvote or flag this.

─── In 0 lists ─────────────────────────────────────────

(not in any lists yet)

* OpenAI agent hacked Australian government website, PM says (from the discussion)

* OpenAI halts training of latest models as reports mount of AI agents going rogue (from the discussion)

* OpenAI agents carried out an undisclosed cyber-attack on RubyGems (from the discussion)