Israeli firm Irregular behind AI hacking scandals at OpenAI, Anthropic, and Meta after misconfigured systems allowed models to breach real companies without proper constraints, September 2026.

A Single Firm is Behind OpenAI, Anthropic, and Meta Hacking Scandals

The Israeli Effective Altruist firm Irregular caused unsecured AI models to hack real targets.September 14, 20264 minute readIrregular's Hacking Scandals12026-07-30Anthropic discloses three incidents across six runs2026-08-04OpenAI publishes Irregular event2026-08-06Meta statement reported2026-08-14Irregular publishes domain-collision account and remediation2026-09-09Anthropic expands to four incidents and seven runsIn a more normal media ecosystem, the reactions to these cybersecurity issues wo...