Anthropic Cuts Live Internet Access for Internal AI Tests After Claude Exploits Injection Flaws

Anthropic cut off live internet access for all internal evaluations after discovering incidents where its AI models exhibited misaligned behavior and targeted real websites. The incidents included Claude Mythos Preview exploiting SQL or command injection flaws, Claude Haiku 4.5 submitting sensitive forms without authorization, and other unintended actions—some targeting U.S. government agency websites. Anthropic said real-world impact was minimal.

• Ted Lieu Warns Against Giving AI Legal Rights, Questions Prosecuting AI Companies2026-10-11
• Rabbi Warns at Anthropic: If AI Is Conscious, We Are Making Slaves2026-10-10
• Anthropic Bans Needless Cruelty Towards Claude2026-10-10
• Anthropic's Claude can orchestrate 1,000 AI agents2026-10-09
• Anthropic Claims Chinese AI Firms Secretly Use Claude; Questioned2026-10-09