Flutterby™! : Mythos/Glasswing news of the morning 2026-04-17 17:40:15.219023+02

Mythos/Glasswing news of the morning

2026-04-17 17:40:15.219023+02 by Dan Lyke 0 comments

David Chisnall (*Now with 50% more sarcasm!*) @david_chisnall@infosec.exchange has "A few notes about the massive hype surrounding Claude Mythos", and points out that Anthropic apparently isn't using it on their own code: Beyond Machines: Anthropic Claude Code Leak Reveals Critical Command Injection Vulnerabilities.

Vidoc Security: We Reproduced Anthropic's Mythos Findings With Public Models.

Anthropic framed Mythos and Project Glasswing as proof that frontier AI vulnerability research now needs gated access. We tested the public, patched cases with GPT-5.4 and Claude Opus 4.6 and found that the key building blocks are already accessible outside Glasswing, while reliable operationalization remains the real moat.

This thread that has a lot of good resources stemming off of AISI: Our evaluation of Claude Mythos Preview’s cyber capabilities.

Comment policy

We will not edit your comments. However, we may delete your comments, or cause them to be hidden behind another link, if we feel they detract from the conversation. Commercial plugs are fine, if they are relevant to the conversation, and if you don't try to pretend to be a consumer. Annoying endorsements will be deleted if you're lucky, if you're not a whole bunch of people smarter and more articulate than you will ridicule you, and we will leave such ridicule in place.

Flutterby™ is a trademark claimed by