Back

Measuring LLMs' ability to develop exploits

Source: Red.Anthropic

Published:

<p>Claude Mythos Preview ’s ability to develop exploits is a step-change over frontier models. This was one of our primary motivations for rolling out the model carefully through Project Glasswing rather than through a general release. Mythos Preview is capable of finding complex vulnerabilities, bu

Read original article

Loading article...

Article not found