251
Over just a few months, ChatGPT went from accurately answering a simple math problem 98% of the time to just 2%, study finds (fortune.com)
submitted 3 years ago by [M, B] to c/technology@lemmy.world
41 comments fedilink hide all child comments
 

Over just a few months, ChatGPT went from accurately answering a simple math problem 98% of the time to just 2%, study finds::ChatGPT went from answering a simple math correctly 98% of the time to just 2%, over the course of a few months.

you are viewing a single comment's thread
view the rest of the comments
[–] 16 points 3 years ago (1 child)

I've been regularly using ChatGPT these last weeks and can confirm it got indeed "dumber"

  • permalink
  • fedilink
  • source
  • hideshow 2 child comments
    •
  • [–] 7 points 3 years ago (1 child)

    That's because they paywalled the good versions, and only corporations get access to that one.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 2 points 3 years ago

    No, even corporations can't get access to the pretrained models.

    And given this is almost certainly the result of the fine tuning for 'safety,' that means corporations are seeing worse performance too (which seems to be the sentiment of developers working with it on HN).

  • permalink
  • fedilink
  • source
  • parent