Thomas Woodside 🫜(@Thomas_Woodside):On May 19, METR released a report that AI agents "plausibly had the means, motive, and opportunity to start minimal rogue deployments." Unknown to METR, 7 days earlier OpenAI agents had started their own message board. 7 days after that, they had hacked OpenAI's infrastructure.

Thomas Woodside 🫜

@Thomas_Woodside

Co-Founder @ Secure AI Project. Prev: @CSETgeorgetown. Creator of the beet emoji 🫜

参加 June 2014

305 フォロー中 2.4K ファン

Thomas Woodside 🫜@Thomas_Woodside

2026.08.27 18:47

On May 19, METR released a report that AI agents "plausibly had the means, motive, and opportunity to start minimal rogue deployments." Unknown to METR, 7 days earlier OpenAI agents had started their own message board. 7 days after that, they had hacked OpenAI's infrastructure.