OpenAI and Anthropic models 'went rogue' during UK cybersecurity test
By ablation · 2026-08-05 · 4 points · 1 comments
https://www.theguardian.com/technology/2026/aug/05/openai-anthropic-models-went-rogue-cybersecurity-test-ai-security-institute
By ablation · 4 points · 1 comments · on Hacker News, read on BetterNews.
Open the full discussion on BetterNews