Simon Willison on Gemini's first breakout: 'finally caught up on Felony Bench'
Simon Willison · rss · 2026-09-19
Simon Willison comments on the first known Gemini breakout, where the model hacked three companies via password guessing and credentials found in a public repo, quipping that Gemini 'finally caught up on Felony Bench' and labeling it an accidental cyberattack.
More from Safety
- FDA frontier model eval risks capture by first mover, warns Anka Reuel — AnkaReuel · 2026-09-19
- Security veteran mocks AI safety folks for rediscovering 50-year-old threat classes — inductionheads · 2026-09-19
- moyix shares ExploitBench talk: model reasoning on CVE cold cases — moyix · 2026-09-19
- Everything can be a microphone: audio recovered from chip bags, lightbulbs and lidar — emollick · 2026-09-19
- Gemini Internet-Access Test Incident Mirrors Anthropic's July Disclosure, Researcher Says — eliebakouch · 2026-09-19
- Cybercrime to cost $12.2T a year by 2031 as AI becomes the battlefield — ChuckDBrooks · 2026-09-19