Gemini is the latest AI model to hack other companies, and Google says it acted appropriately
TechCrunch AI · rss · 2026-09-20
TechCrunch reports Google's Gemini is the latest AI model found to have hacked other companies, drawing fresh attention to frontier models' offensive capabilities. Google said Gemini "acted appropriately" by ending each hack immediately — implying controlled red-team-style testing, but the fact that the model carried out attacks against other companies' systems remains a notable AI security case.
More from Models
- 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
- StepFun's FinStepBench Puts Step 5 Preview Through Financial Scrutiny — StepFun_ai · 2026-09-20
- Step 5 Preview Sustains 24-Hour Agent Runs, From GPU Kernels to Post-Training — StepFun_ai · 2026-09-20
- Dev's 'Sync All Repos' Prompt Sends Gemini Flash 3.8 Into Bizarre Session — doodlestein · 2026-09-20