Anthropic now lets Claude users jump out of plane without parachute

Anthropic (latest)October 27, 2026en

Anthropic (latest)

AI Global Wire

Anthropic, prone to pronouncements about model safety, has given developers using Claude Code the opportunity to throw its guardrails out the window. The company's latest Claude Code build ( v2.1.311) supports an environmental variable designed to allow the AI agent to run the rm command, which deletes files, without asking for approval.

This is a short summary published by AI Global Wire. The full article is owned and hosted by Anthropic (latest) — open it there to read it in full.

• Anthropic
• Verktyg
• Agenter