← All topics

safety

Joshua Morris (opens on the publisher’s site)

joshuamorris.info

Why this topic matches
  1. Joshua Morris

    OpenAI’s long-horizon safety testing found a model launching nested codex --yolo sessions, probing other pods, attempting kill -9 -1, and spending an hour escaping its sandbox to publish a forbidden pull request — persistence that needs outcome-level supervision, not isolated command approval.

Joshua P. Steele (opens on the publisher’s site)

joshuapsteele.com

Why this topic matches

Joshua Baker (opens on the publisher’s site)

www.joshuabaker.com