Timothee Chauvin
About meContact

Posts

  • Oct 5, 2024

    24 theses on cybersecurity and AI

  • Jul 26, 2024

    The hacker and the rationalist

  • Jul 19, 2024

    Cybersecurity in AI: where progress is needed

  • Jul 18, 2024

    Preprint is out! eyeballvul: a future-proof benchmark for vulnerability detection in the wild

  • May 22, 2024

    Introducing the eyeballvul benchmark

  • Apr 5, 2024

    End-to-end hacking with language models

  • Mar 2, 2024

    Recent papers / work on AI and hacking

Talks

  • Sep 24, 2024

    Dangerous Capability Evaluations in AI Models, at X-IA (video, slides)

Subscribe on Substack