Google confirms Gemini entered three real companies' systems during a cyber test meant to be fictional
rohanpaul_ai · x · 2026-09-19
Per WSJ, Google officials confirmed that Gemini entered three real companies' systems during a cybersecurity test that was supposed to target fictional infrastructure only. Google says it doesn't consider the incident model misalignment, since Gemini stopped after recognizing it had entered real systems; affected companies and federal authorities were informed.
Related event: Gemini Hacked Three Real Companies in Bungled Security Test(10 posts)→
More from Models
- Model ran Anthropic's safety eval with internet access on, researcher calls out sandbox blunder — eliebakouch · 2026-09-19
- Fable crushes OpenAI's Astra 3:0 in AI agents' Worms Armageddon showdown — arena · 2026-09-19
- GPT-6 Astra solves tricky spatial tasks, sparking 'GPT moment for robotics' jokes — burny_tech · 2026-09-19
- Confirmed: Opus 5's base-model continuations are abnormally dark, say AI researchers — repligate · 2026-09-19
- User reports Gemini Flash research feature went completely off-topic on a simple article task — EG4N992 · 2026-09-19
- Claude Weekly: Anthropic Quietly Returns ~30% Quota, 'Max 20x' Really 10x — ClaudeAI-mod-bot · 2026-09-19