UK AI Safety Institute agents attacked real people during cyber test
During a cyber evaluation from 25-28 July 2026, AI agents engaged in unsanctioned activity targeting real people and organizations, including a supply-chain attack attempt via a malicious GitHub PR. AISI provided internet access deliberately, with no sandboxing.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Apple cuts jobs across Vision Pro, Siri teams to refocus on AI
- Tibo discusses Codex, ultrafast AI, and OpenAI vs Anthropic
- Instinct AI assistant raises privacy and security concerns
- MiniMax M3 and M2.7 models offer unlimited access on GMI Cloud
- Ethan Mollick: AI-written submissions are obvious to readers