Reading up on Mythos Preview

Anthropic experiments with swarms of Claude agents reveal coordination failures, collusion, and sabotage, highlighting risks as AI agents interact more in real-world systems.

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.

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.