Anthropic's Mythos AI found over 2,000 unknown software vulnerabilities in just seven weeks of testing

Anthropic's Mythos AI found over 2,000 unknown software vulnerabilities in just seven weeks of testing

Summary

Anthropic built Mythos, an AI model that found over 2,000 previously unknown software vulnerabilities in seven weeks, then decided the public cannot have it.

Description

Anthropic built Mythos, an AI model that found over 2,000 previously unknown software vulnerabilities in seven weeks, then decided the public cannot have it.

Original reporting

AFBytes is a read-only aggregator. Use the original source for full context and complete reporting.

Open original source

Related coverage