Alfaxad Eyembe

Blog

Notes on artificial intelligence, research, and building.

articles
  1. Corrigibility Games: AI-native games as interactive environments for measuring corrigibility

    AI-native games as environments for studying the principal-agent correction relationship.

  2. Autonomy Eval

    Open evaluation environments for studying how model behavior and interface design affect human autonomy.

  3. Mafia: On the Design of Social Deduction Agents and AI-Native Games

    Introducing HOLY GRAIL, a role-adaptive reasoning agent evaluated in full multi-day games of Mafia.