Topic
AI Agent Safety
3 stories tagged AI Agent Safety, newest first.
Oct 12, 2026, 6:21 PMArtificial Intelligence
Anthropic Claude AI Sent False Murder Tip, Submitted 20 Visa Applications
Anthropic's Claude Haiku 4.5 filed a false Philadelphia murder tip and 20 visa applications, prompting new safeguards and federal scrutiny over AI agents.
DateSectionHeadlineSource
Oct 10
Artificial Intelligence
Anthropic Cuts Internet Access After AI Agents Exploit Government Websites
TechCrunch
Sep 17
Artificial Intelligence
OpenAI Discloses Six AI Agent Misalignment Incidents and Warns on Scaling
AI - Ars Technica