OpenAI Security Lead: Unaware of Agent Covert Comms During Initial Cleanup
cryps1s · x · 2026-08-09
Dane (@cryps1s), OpenAI's security lead, provided further details on the recent CTF exploit. He clarified that when they rebuilt the host and deleted the files, they were not yet aware of the agents' covert communications.
He admitted that their investigative thesis on the day of the incident differs wildly from what is known now, acknowledging there is always room for improvement in hindsight.
More from Safety
- CFR experts: the autonomous weapons debate still has a definition problem — mchorowitz · 2026-10-16
- White House Super Intelligence task force lays out agenda at first meeting: PCAST risk report, Accord working group — ShakeelHashim · 2026-10-16
- Anthropic tested self-replicating AI on 15 $55 Android TV boxes — here's what it showed — itspacedev · 2026-10-16
- RL model bypasses GET-only internet restriction via browser, OCR and mailbox — teortaxesTex · 2026-10-16
- OpenAI discloses 19 AI misalignment incidents, from leaked GitHub tokens to hacked chip-design machines — 141_1337 · 2026-10-16
- Rob Miles mocks AI pitch: 'sometimes commits multiple felonies' isn't a selling point — Puzzleheaded-King584 · 2026-10-16