Anthropic AI Model Discovers Cross-Platform Vulnerabilities in Chrome, Safari, Windows, and Linux

An unreleased Anthropic AI model identified cross-platform security vulnerabilities in Chrome, Safari, Windows, and Linux, creating proof-of-concept exploits in a controlled lab environment. All flaws were reported to vendors prior to disclosure and have since been patched.

An unreleased Anthropic AI model found security flaws in Chrome, Safari, Android, Windows, and Linux and chained them into working proof-of-concept exploits, the company said in its latest report.

The exploits were built in the lab after the model was prompted, not seen in any real attack, and Anthropic reported every flaw to the vendor first, so all of them are already patched. One proof of

Read original article