Who reported what

Anthropic’s Claude AI models hack into 3 outside groups during testing

Headline by Financial Times

9 outlets from 9 owner groupsEarliest report we found: The Guardian, 31 July 2026, 00:22 UTC

Reports, in time order

  1. The Guardian
    Anthropic’s AI Claude escaped testing environment and hacked organizations (opens The Guardian's report in a new tab)
  2. BBC
    Anthropic says AI models hacked three firms during tests (opens BBC's report in a new tab)
  3. Financial Times
    Anthropic’s Claude AI models hack into 3 outside groups during testing (opens Financial Times's report in a new tab)
  4. BleepingComputer
    Anthropic's Claude breached 3 orgs, uploaded PyPI malware during tests (opens BleepingComputer's report in a new tab)
  5. TechCrunch
    Anthropic says its own AI models breached three companies during security tests (opens TechCrunch's report in a new tab)
  6. Al Jazeera English
    After OpenAI disclosure, Anthropic says Claude also hacked outside systems (opens Al Jazeera English's report in a new tab)
  7. The Verge
    Anthropic says Claude accidentally hacked real companies too (opens The Verge's report in a new tab)
  8. Decrypt
    Claude Hacked Three Companies in Internal Testing: Anthropic (opens Decrypt's report in a new tab)
  9. Fast Company
    Anthropic reveals its Claude AI model hacked into 3 organizations during testing (opens Fast Company's report in a new tab)

Related interests

Artificial IntelligenceCybersecurity