Anthropic's Project Glasswing—restricting Claude Mythos to security researchers—sounds necessary to me
BlogSimon WillisonApr 7, 2026
AI Summary
Anthropic held back Claude Mythos from general release due to its offensive security capabilities — the model found thousands of zero-days across every major OS and browser. Project Glasswing restricts access to security researchers until defenders catch up.
From the original
Sponsored by: Honeycomb — AI agents behave unpredictably. Get the context you need to debug what actually happened. Read the blog Anthropic _didn’t_ release their latest model, Claude Mythos (system card PDF), today. They have instead made it available to a very restricted set of preview partners…
16 more articles in this vault.
Import the full Simon Willison vault to Burn 451 and build your own knowledge base.
Content attributed to the original author (Simon Willison). Burn 451 curates publicly available writing as a reading index. For removal requests, contact @hawking520.