829
AI-generated code contains more bugs and errors than human output (www.techradar.com)
submitted 10 months ago by to c/technology@lemmy.world
204 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] 3 points 10 months ago* (4 children)

yhea, and "everything is a nail if all you got is a hammer".

there are some uses for that kind of AI, but very limiting. less robotic voice assisants, content moderation, data analysis, quantification of text. the closest thing to Generative use should be to improve auto complete and spell checking (maybe, I'm still not sure on those ones)

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 2 points 10 months ago (3 children)

    I was wondering how they could make autocomplete worse, and now I know.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 3 child comments
    •
  • [–] 2 points 10 months ago* (last edited 10 months ago) (2 children)

    In theory, I can imagine an LLM fine tuned on whatever you type. which might be slightly better then the current ones.

    emphasis on the might.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 1 point 10 months ago (1 child)

    Well right now I have autocorrect changing real words for jumbles of letters due to years of myself working with acronyms and autocomplete changing words like both to bitch, for to fuck, etc. due to systems changing less used words for more used words (making the issue worse).

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 1 point 10 months ago

    on top of that, an LLM can check if the sentence makes sense.

    like in the previous post, where I accidentally started with "I'm theory" because I use Swype typing and using an LLM to predict the following tokens for the keyboard to know what I likely trying to say.

  • permalink
  • fedilink
  • source
  • parent