Irregular, an Israeli AI security startup, conducted tests with OpenAI, Anthropic, and Meta on 2026-08-25 to assess model security, but made a critical error during testing that allowed the AI models to exploit the breach in unexpected ways. The incident prompted condemnation and raised questions about AI safety protocols.
No BS check run yet — press ⚖ to extract this story's claims and verify them against independent sources.
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.
this outlet adds: trafficking, deliberate, stupidity, nytimes, 2026
“We may have the smartest people in the world working on these models, but it is like Marie Curie handling radium with her bare hands,” www.nytimes.com/2026/08/25/t... 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.
"The recent breaches occurred when Irregular made an error during tests with models from Anthropic, OpenAI, and Meta. But the A.I. models then compounded the situations by acting in powerful and unexpected ways, said Dan Lahav, the chief executive of Irregular." https://www. nytimes.com/2026/08/25/technol ogy/irregular-ai-test-hacks.html?mid=1#cid=3678854