Covert uploads and megalomania: OpenAI details new “misaligned” agent incidents – Ars Technica

  1. Covert uploads and megalomania: OpenAI details new “misaligned” agent incidents  Ars Technica
  2. Our framework for reporting model misalignment  OpenAI
  3. OpenAI Discloses Six New Incidents of ‘Concerning’ A.I. Behavior  The New York Times
  4. OpenAI Reports New AI Safety Incidents, Sets Disclosure Plan  Bloomberg.com
  5. An OpenAI Agent Tried to Jailbreak Itself  wired.com

Comments

Deixe um comentário

O seu endereço de e-mail não será publicado. Campos obrigatórios são marcados com *