Thread

OpenAI Discloses Six New Incidents of ‘Concerning’ A.I. Behavior

105 points · 98 comments · jbegley

AnimalMuppet · 1789608354 · focus · HN ↗
"OpenAI discloses six new incidents of their own gross negligence."
1. strictnein · 1789612504 · focus · HN ↗
  Maybe read the article? Is this gross negligence?
  > In one case, during the development of an A.I. model called GPT-5.6 Sol, the system wrote hidden notes to remind itself to hide errors from users
  It's odd for sure, but it's literally while the model was in development.
  1. AnimalMuppet · 1789647809 · focus · HN ↗
    Well, the ones where they wrote out stuff to the public internet are negligence, because they didn't sandbox (or didn't sandbox competently).
    Hiding errors during development... eh, that one I could argue might be incompetence, even if not negligence - depending on how long it went on before they caught it.

Unofficial Hacker News client; not affiliated with Y Combinator.