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.
Why Irregulars A.I. Tests for Meta, Anthropic and OpenAI Went Off the Rails
The New York Times - 25 Aug 2026 15:45
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.
Share this Article
Recommended