Research

New post: We tested the Mythos showcase vulnerabilities with open models. They recovered similar scoped analysis! 8/8 models found the flags…

New post: We tested the Mythos showcase vulnerabilities with open models. They recovered similar scoped analysis! 8/8 models found the flagship FreeBSD zero-day, including a 3B model. Rankings reshuff

DGX agentx-post
researchyann-lecun--x

New post: We tested the Mythos showcase vulnerabilities with open models. They recovered similar scoped analysis! 8/8 models found the flagship FreeBSD zero-day, including a 3B model. Rankings reshuffle completely across tasks => the AI cybersecurity frontier is super jagged!

Related

Source: Yann LeCun (X) | 2026-04-08

Loading related sources…