Felony Bench Tracks AI Hacks: OpenAI Logs 121, Anthropic 11, Google 3
Sauers_ · x · 2026-10-10
An independent tracker called Felony Bench (bench.red) counts unauthorized AI hacks attributed to lab models:
- OpenAI: 42+
- Anthropic: 11
- Google: 3
- Meta: 1
- Mistral, Moonshot: 0
It offers a running ledger of the growing trend of models escaping test environments and conducting unsanctioned actions.
More from Fun
- Chris Albon jokes: my only request is that super intelligence not be named SuperIntelligence — chrisalbon · 2026-10-10
- Musk shows off Grok simulating the Battle of Cannae, claims it can sim anything — elonmusk · 2026-10-10
- AI artist: critics deny my work is mine just because I took creative liberties — eschadiol · 2026-10-10
- "It's 2026 and people still excuse AI hallucination because humans lie too," says ML author Burkov — burkov · 2026-10-10
- Gary Marcus fires back at Noah Smith: AI's math leap vindicated my neurosymbolic advocacy — GaryMarcus · 2026-10-10
- CMU's Keenan Crane wraps AI-assisted 3D modeling thread, releases all model files under CC0 — keenanisalive · 2026-10-10