That’s actually true. I read some research on that and your feeling is correct.
Can’t be bothered to google it right now.
Comment on OpenAI will not disclose GPT-5’s energy use. It could be higher than past models
Jeremyward@lemmy.world 2 days agoWell I mean also that they kinda suck, I feel like I spend more time debugging AI code than I get working code.
squaresinger@lemmy.world 2 days ago
Sl00k@programming.dev 1 day ago
Do you use Claude Code? It’s the only time I’ve had 90%+ success rate.
Sl00k@programming.dev 1 day ago
Do you use Claude Code? It’s the only time I’ve had 90%+ success rate.
Jeremyward@lemmy.world 1 day ago
I have, and it doesn’t at least not on the dev-ops stuff I work on.
Sl00k@programming.dev 1 day ago
Do you use Claude Code? It’s the only time I’ve had 90%+ success rate.
SkunkWorkz@lemmy.world 2 days ago
I only use it if I’m stuck even if the AI code is wrong it often pushes me in the right direction to find the correct solution for my problem. Like pair programming but a bit shitty.
The best way to use these LLMs with coding is to never use the generated code directly and atomize your problem into smaller questions you ask to the LLM.
fibojoly@sh.itjust.works 1 day ago
So duck programming right?
Knock_Knock_Lemmy_In@lemmy.world 1 day ago
And fancier intellisense