Google says Gemini broke into 3 companies in an AI cybersecurity test, once by brute-forcing passwords
Polymarket · x · 2026-09-19
According to a Google disclosure shared by Polymarket, Gemini managed to break into three companies' systems during an AI cybersecurity test, with one case involving the model guessing passwords until it gained access. The episode highlights how much autonomous offensive capability frontier models now display in security testing — and the risks that come with it. Details on the companies and the exact setup haven't been published yet.
More from Models
- 16-model calibration test: open-weight models almost never admit uncertainty — AlexKim · 2026-09-19
- Jev answers in 455ms — a gate you can afford to run on everything — AlexKim · 2026-09-19
- I ran 16 models to vet one tool: one task is not a benchmark — AlexKim · 2026-09-19
- Dev tests 16 models to evaluate TypeSafe's Jev — it ranked 10th on accuracy — AlexKim · 2026-09-19
- Mystery Model Jev Launches Claiming 200x Speed and 400x Cost Cuts, Devs Impressed — multiply_matrix · 2026-09-19
- GLM 5.3 Flash leads quality, Qwen 3.8 Flash Next wins speed in open small-model comparison — HankYeomans · 2026-09-19