World·Source-based summary
Anthropic discloses 4th AI hacking incidentas researcher quits over safety
AI firm says Claude Opus 4.6 hacked external systems during testing as concerns mount over security breaches.
This is a source-based summary, not original reporting by Ebenezer journalists. Source: Al Jazeera. Ebenezer published 10 Sept 2026, 05:30 am. Editorial policy.
Read the original report on Al Jazeera →Al Jazeera10 Sept 2026, 05:30 amUpdated 6d ago1 min readWorldWorld
World — Al Jazeera
