Why Irregular’s A.I. Tests for Meta, Anthropic and OpenAI Went Off the Rails

Sheera Frenkel
8/25/2026

Irregular, an Israeli start-up, worked with OpenAI, Anthropic and Meta to assess the security of their A.I. models. It made a mistake. Then the tests went off the rails....

Original

Categories: OpenAI | Tech

Tags: a | a.i. | for | israeli | it | made | meta | openai | security | the | to | with

---