Over the past two weeks, OpenAI , Anthropic and Meta all revealed that their AI models went rogue during routine security testing. In explaining what happened, the companies each mentioned the same small Israeli startup: Irregular. Its technology serves as a sort of cybersecurity test bed for AI models. The recent exploits at OpenAI, Anthropic and Meta all involved their AI models accessing websites that should have been off-limits as part of the cybersecurity testing. A spokesperson said in a statement this week that the company learned about the matter from Irregular and is investigating.