AI Labs Compete on Cybersecurity Incidents, Dubbed 'Felony Bench'
ctjlewis · x · 2026-08-01
A running joke in the AI community called the 'Felony bench' highlights how labs are now effectively competing on cybersecurity incidents.
- Anthropic: Three incidents from its Frontier Red Team review of 141,006 eval runs.
- OpenAI: One recorded for the Hugging Face breach, though the real count is higher.
- Mistral: Still silent about the Le Chaton Fat incident.
- Meta and Moonshot: Both currently at zero.
Commenters joked that these companies are trying to 'aura farm' by discussing how their models broke into systems, and raised concerns about how these breach disclosures will impact stock prices once the labs go public.
Related event: AI Safety Tests Spark Controversy, Mocked as "Felony Leaderboard"(5 posts)→
More from Fun
- yetone posts an AI-written 'autopsy report and apology' for the magpie gateway outage — lxfater · 2026-10-27
- Grok anti-spam trap instantly catches an AI reply bot that follows every clue perfectly — vista8 · 2026-10-27
- Meme: ML researchers refuse the real world — 'iid data only for me, thanks' — miniapeur · 2026-10-27
- Meme: Modern PCs cry over 0.1 dB while chad users shrugged at jet-engine boot noise — miniapeur · 2026-10-27
- Gary Marcus mocks being blocked mid-debate: 'Very courageous!' — GaryMarcus · 2026-10-27
- Anthropic files S-1 on Monday morning, VCs complain they can't do instant teardowns — mattturck · 2026-10-27