OpenAI and Anthropic Disclose Incidents in Shared AI Security Testing Environment

TechNadu · x · 2026-08-06

Both OpenAI and Anthropic have disclosed incidents involving the same AI security testing environment operated by Israeli startup @Irregular.

Neither company stated that an AI model "escaped"; rather, they attributed the events to issues within the testing infrastructure.

Related event: OpenAI Discloses Third-Party Testing Mishaps: Infrastructure Flaws, Not Model Jailbreaks(12 posts)→

Original post →

More from Safety

Safety channel →