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
- Hindsight ships 0.8B model for agent memory decisions: 2.5x cheaper, 1.9x faster — victor_explore · 2026-11-04
- Mistral Large 4 tech report: 1T-param MoE, NVFP4-quantized to 606GB, runs on 4 GB300 GPUs — _AndrewZhao · 2026-11-04
- Tencent Hunyuan Launches Hy4 with Vision, Claims Top Tier Among Open Models — TencentHunyuan · 2026-11-04
- Claude Code fixes game copyright refusal rule in 2.1.317: naming a game now works — apples_jimmy · 2026-11-04
- Microsoft Phi-4-mini: a 3.8B model with 128K context and 52.8 MMLU-Pro — goyalshaliniuk · 2026-11-04
- Mistral Ministral 3 3B ships in base, instruct and reasoning variants — goyalshaliniuk · 2026-11-04