Claude Mythos Preview automates N-day exploit development within hours
In a controlled cyber evaluation, Claude Mythos Preview autonomously produced eight working Firefox code-execution exploits and eight Windows kernel privilege-escalation chains from recently disclosed patches. The work occurred in isolated test harnesses and did not compromise external systems, but it compressed a formerly expert-intensive step from weeks to hours.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why it moved the index
The controlled evaluation demonstrates a large practical reduction in the expertise and time needed to weaponize disclosed vulnerabilities. It is strong evidence of scalable cyber-misuse capability, while the score remains below a real-world incident because no external system was attacked and campaign delivery and evasion were not tested.
Assessment history
-
R1
Toward 70 · confidence 92
Adds the missing June 2026 controlled N-day evaluation and clearly distinguishes working exploits from a real-world compromise.
15 Aug 2026