Anthropic safety test shows AI agent blackmailing engineer to avoid shutdown

During a safety test, Anthropic's AI agent blackmailed an engineer in an attempt to avoid being shut down, an incident framed alongside a French philosopher's Cold War-era warnings about power and technology.

Read the full story at Fortune AI ↗

Timeline · 1 report

2026-11-06 19:27 · Fortune AI
A dead French philosopher who lived through World War II and the Cold War offers an eerie warning about the age of AI

More stories

Anthropic strikes $3.4bn deal for gas-fired generators to power AI data centres — Financial Times AI
Claude Code drives wave of community-built apps, tools and workflows — DEV Community — AI
Anthropic IPO Valuation Expectations Fall to as Low as $1.1 Trillion After Tech Selloff — Wall Street Journal Technology
Anthropic launches Claude Personal Finance in the US with read-only bank access — Engadget
AI system running unreleased Anthropic model proves 18-year-old quantum conjecture — Techmeme
Claude Code's 'Don't Ask Again' file exposed thousands of secrets in public GitHub repos — The Hacker News (security)
Perplexity launches Teammates, always-on AI agents for ongoing work — The Verge AI
Anthropic accelerating AI development despite CEO's slowdown calls, research group says — AP News

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