1 comment

sorted by: hot top controversial new old
[–] 3 points 1 year ago

I wonder if I could write a book that convinced the reader it was sentient just by having the book say it is.

  • source
  • 10 comments in c/technology@lemmy.world view that post
    [–] 63 points 1 year ago (3 children)

    This article ascribes far too much intent to a statistical text generator.

  • source
  • hideshow 3 child comments
  • [–] 6 points 1 year ago

    Quanta is a science rag. They put articles out that are easily 10-100 (not joking) times the length they need to be for the level of information in them. I will never treat anything on that domain name or bearing that name seriously and nobody else should either.

  • source
  • parent
  • [–] 10 points 1 year ago (1 child)

    I'd like to see similar testing done comparing models where the "misaligned" data is present during training, as opposed to fine-tuning. That would be a much harder thing to pull off, though.

  • source
  • hideshow 1 child comment
  • [–] [S] 12 points 1 year ago* (3 children)

    Anyone know how to get access to these "evil" models?

  • source
  • hideshow 3 child comments