Comment

Wrong 70% doing what?

I’ve used LLMs as a Stack Overflow / MSDN replacement for over a year and if they fucked up 7/10 questions I’d stop.

Same with code, any free model can easily generate simple scripts and utilities with maybe 10% error rate, definitely not 70%

Sort:hotnew top

CodeBlooded@programming.dev ⁨1⁩ ⁨week⁩ ago
I’m far more efficient with AI tools as a programmer. I love it! 🤷‍♂️

source
floo@retrolemmy.com ⁨1⁩ ⁨week⁩ ago
Yeah, I mostly use ChatGPT as a better Google, and if I kept getting wrong answers, I wouldn’t use it either.

source
- Imgonnatrythis@sh.itjust.works ⁨1⁩ ⁨week⁩ ago
  Same. They must not be testing Grok or something because everything I’ve learned over the past few months about the types of dragons that inhabit the western Indian ocean, drinking urine to fight headaches, the illuminati scheme to poison monarch butterflies, or the success of the Nazi party taking hold of Denmark and Iceland all seem spot on.
  
  source
- dylanmorgan@slrpnk.net ⁨1⁩ ⁨week⁩ ago
  What are you checking against? Part of my job is looking for events in cities that are upcoming and may impact traffic, and ChatGPT has frequently missed events that were obviously going to have an impact.
  
  source
  - lepinkainen@lemmy.world ⁨1⁩ ⁨week⁩ ago
    LLMs are shit at current events
    
    Perplexity is kinda ok, but it’s just a search engine with fancy AI speak on top
    
    source
TimewornTraveler@lemmy.dbzer0.com ⁨1⁩ ⁨week⁩ ago
it specifies the tasks in the article

source
Imgonnatrythis@sh.itjust.works ⁨1⁩ ⁨week⁩ ago
Definitely at image generation. Getting what you want with that is an exercise in patience for sure.

source