FAR Research: Adversarial Policies Beat Superhuman Go AIs

Поделиться
HTML-код
  • Опубликовано: 18 окт 2024
  • FAR Research: "Adversarial Policies Beat Superhuman Go AIs"
    📝 Check out the blog post: far.ai/post/20...
    📄 Read the full paper: arxiv.org/abs/...
    🔗 Visit our website: goattack.far.ai
    Work by Tony T. Wang, Adam Gleave, Tom Tseng, Kellin Pelrine, Nora Belrose, Joseph Miller, Michael D. Dennis, Yawen Duan, Viktor Pogrebniak, Sergey Levine, Stuart Russell
    #aisafety #airesearch

Комментарии •