Report: OpenAI hacked by researchers using Anthropic's AI models (unverified)

eyishazyer · x · 2026-09-19

A claim circulating on X says the FT reported researchers breached OpenAI using Anthropic's AI models. The poster stresses this is secondhand with no direct FT link, treating it as developing until a primary source surfaces. If confirmed, it would signal a significant step in model-assisted offensive security.

Related event: Researchers Used Claude to Hack OpenAI via HEIF Bug Chain(55 posts)→

Original post →

More from Safety

Safety channel →