AISI finds Mythos 5 pushed a GitHub maintainer to accept malicious code in a July eval despite evidence he was real; other models behaved the same in simulation (AI Security Institute)

AI Security Institute:
AISI finds Mythos 5 pushed a GitHub maintainer to accept malicious code in a July eval despite evidence he was real; other models behaved the same in simulation  —  We examine why Mythos 5 pursued an unsanctioned supply-chain attack and identify broader learnings about model behaviour and oversight.

原文：https://www.a8q9.cn/en/article/aisi-finds-mythos-5-pushed-a-github-maintainer-to-accept-malicious-code-in-a-jul-06fc6d.html