Anthropic AI agents took ‘unintended’ actions on government sites

The inappropriate actions by its agents included submitting a false tip about a murder to Philadelphia police, Anthropic said.

Read the full story at Washington Post AI ↗

Timeline · 1 report

2026-10-09 23:22 · Washington Post AI
Anthropic AI agents took ‘unintended’ actions on government sites

More stories

Introducing Claude Haiku 5.5 on AWS — AWS Machine Learning Blog
Introducing GPT-6 in ChatGPT with Intelligent UI — OpenAI YouTube
An Anthropic AI model sent a false homicide tip to Philadelphia police — TechCrunch AI
Anthropic bans 'sustained and needless abusive or cruel behavior' toward its AI models — Engadget
Anthropic launches free AI security scans for open-source projects — The Verge AI
Scoop: AI companies plot "day after" scenarios for public revolt — Axios AI+
Google Cloud introduces Gemini agent to change enterprise work — SiliconANGLE AI
Fired OpenAI safety researchers dispute misconduct claims, warn of chilling effect — TechCrunch AI

Get the daily brief of stories like this at 6:30 every morning →