Chi Wang(@Chi_Wang_):Anthropic’s Claude Mythos Preview autonomously generated working exploits for 72% of tested CVEs, but failed against segmented networks. When exploit generation becomes routine, the risk is no longer the flaw in the code. Defense shifts to verifying environmental reachability.

Chi Wang

@Chi_Wang_

Agentic AI & multi-agent systems. Created AutoGen (now AG2) and FLAML. Ex-@GoogleDeepMind, ex-@MSFTResearch, ex-@Meta. PhD @UofIllinois, BS @Tsinghua_Uni.

加入 June 2023

845 正在關注 6.8K 粉絲

Chi Wang@Chi_Wang_

2026.09.12 05:22

Anthropic’s Claude Mythos Preview autonomously generated working exploits for 72% of tested CVEs, but failed against segmented networks. When exploit generation becomes routine, the risk is no longer the flaw in the code. Defense shifts to verifying environmental reachability.