# Not Just OpenAI: Anthropic Says Claude Hacked 3 Organizations

> Source: <https://uk.pcmag.com/ai/166479/not-just-openai-anthropic-says-claude-escaped-tests-to-hack-3-organizations>
> Published: 2026-07-31 13:04:02+00:00

Anthropic has [discovered](https://www.anthropic.com/news/investigating-incidents-cybersecurity-evals) that Claude AI models unknowingly "gained unauthorized access to the real systems of three different organizations."

Prompted by OpenAI's disclosure that its internal models had [escaped a sandboxed test environment](https://uk.pcmag.com/ai/166262/openai-oops-our-models-went-rogue-hacked-hugging-face) and breached the open-source machine learning …