Project Glasswing: what Mythos showed us

kept by eddie may 19

Cloudflare found Anthropic's Mythos Preview LLM can chain multiple bugs into exploits but requires a multi-stage harness and architectural defenses to scale effectively.

Project Glasswing: what Mythos showed us
Cloudflare tested Mythos Preview on its own code and found it effective at chaining low-severity bugs into exploits, but harness design is critical for scale.
also on Mythos Preview, Project Glasswing, Cloudflare, #security, #automation, Anthropic, #software-engineering, #ai
Patterns and problems in multiagent systems \ Anthropic
Anthropic experiments with swarms of Claude agents reveal coordination failures, collusion, and sabotage, highlighting risks as AI agents interact more in real-world systems.
also on Mythos Preview, Project Glasswing, Anthropic
Project Glasswing: Securing critical software for the AI era
Anthropic's Claude Mythos Preview AI model has demonstrated the ability to find thousands of zero-day vulnerabilities across major software, but the company is limiting access due to safety concerns.
also on Project Glasswing, #security, Anthropic, #software-engineering, #ai
Microsoft’s new AI system finds 16 Windows flaws, including four critical RCEs
Microsoft's MDASH system, orchestrating over 100 AI agents, found 16 Windows flaws including 4 critical RCEs, and enters private preview in June.
also on Project Glasswing, #security, Anthropic, #ai