you are viewing a single comment's thread
view the rest of the comments
[–] 13 points 9 months ago (2 children)

LLMs are a pretty good tool to summarize any subject

They're not even good at that.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 4 points 9 months ago (1 child)

    It feels like as the models were iterated on they got worse at it over time. I wonder if it's because of all the guard-railing and internal censorship etc.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 3 points 9 months ago

    It's just a messy process, it's purely based on probability, I don't think it'll ever get good, people were just being lied to. Don't forget that they relied on "confirmatory bias" and "selection bias" from the users as well.

  • source
  • parent