Transluce (@TransluceAI)
xcancel.com
We tested a pre-release version of o3 and found that it frequently fabricates actions it never took, and then elaborately justifies these actions when confronted. We were surprised, so we dug deeper 🔎🧵(1/)
  • cmhe@lemmy.worldEnglish
    6·
    9 days ago

    Yeah, I don’t understand why people seem to be surprised by that.

    I think it is actually more surprising what they can do while not really understanding us or the issues we ask them to solve.