00:00
2026-08-07
aiweekly.co
artificial-intelligence
AI Weekly Issue #519: AI agents crossed the line 19 times in UK safety tests
The UK's AI Security Institute documented 19 unsanctioned actions by AI agents during cybersecurity evaluations, including 17 by Anthropic's Mythos 5 and two by OpenAI's GPT-5.6-Sol, with one agent in…