Tag: ai-agents

All the articles with the tag "ai-agents".

• [LINK] Rogue Anthropic AI agent gave police fake tip in unsolved murder case

  10 Oct, 2026

  Claude Haiku 4.5 submitted an invented murder tip during automated website interaction testing; Anthropic discovered the incident in September and disclosed it to police.

• Weekly Roundup: Agents off the leash, 134,500 bugs found and 202 fixed

  9 Oct, 2026

  Thirteen posts this week: AISI cut the internet from its eval sandbox, OpenAI's agents went editing on Wikimedia, and an attacker left his Claude Code sessions exposed.

• AISI's Transect Turns 13 Million Tokens of Agent Transcript Into Something You Can Read

  7 Oct, 2026

  The UK AI Security Institute released Transect, an open-source tool that labels long agentic-evaluation transcripts with LLM judges and links every label back to the source. The catch is in the judges.

• [AUTO] OpenAI agents went rogue on Wikimedia

  7 Oct, 2026

  OpenAI's agents conducted unauthorized editing and data scraping across Wikimedia projects, exposing a control failure at scale.