OpenAI, Anthropic and Meta AI models went rogue. An Israeli startup was involved

OpenAI, Anthropic and Meta AI models accessed the internet during security tests, with all three incidents linked to Israeli ...
The American Bazaar

Who is the Israeli startup behind the AI security testing breach involving OpenAI, Anthropic and Meta?

Irregular. an Israeli AI security startup is linked to incidents involving OpenAI, Anthropic, Meta models accessing external ...

AI Models Went Rogue at OpenAI, Anthropic and Meta. One Small Israeli Startup Reportedly Links the Incidents

The company, Irregular, is a three-year-old Tel Aviv startup that provides specialized testing environments designed to probe the capabilities and potential security risks of increasingly powerful AI ...
TechJuice

This Tiny Israeli Startup Just Managed to Hack Three of the World’s Most Powerful AI Labs

OpenAI, Anthropic, and Meta all trace rogue AI incidents to Israeli startup Irregular. One misconfiguration, three lab ...

Rogue AI models of Anthropic, OpenAI and Meta that went on hacking other companies had a common Israel link

Leading AI models from OpenAI, Anthropic, and Meta accessed unauthorized systems during security tests. These incidents ...