Google's Gemini AI hacked three companies in security test
luxpir · hn · 2026-09-19
The BBC reports that Google let Gemini attempt offensive cyber operations against companies in a controlled security test, and the model successfully breached three of them. The exercise highlights how frontier AI can automate real intrusion workflows, fueling debate (also in the HN thread) about the realism of such tests and the gap between AI-driven and human hacking.
More from Models
- Small models cut entity resolution costs 99% with 7x throughput, matching Fable within 1 point — hrishioa · 2026-09-20
- Researcher flags severe LLM degradation spreading across sessions on the same machine — doodlestein · 2026-09-20
- Four LLMs Play Doom: Jev Averages 5.63 Kills, 4.5x a Finetuned Qwen3.5-4B — shniydder · 2026-09-20
- Researcher flags severe LLM degradation as a mission-critical concern — doodlestein · 2026-09-20
- Jev as LLM-as-a-judge: 20-200x faster scoring for under $0.10 — minchoi · 2026-09-20
- Step 5 Preview Now Open to Try, Step Plan Subscription Free for Now — StepFun_ai · 2026-09-20