The study tracked around 800 developers, comparing their output with and without GitHub’s Copilot coding assistant over three-month periods. Surprisingly, when measuring key metrics like pull request cycle time and throughput, Uplevel found no meaningful improvements for those using Copilot.
I’ve tried it for even some boiler plate code a few times. I’ve had to end up rewriting it every time.
It makes mistakes like Junior engineers, but it doesn’t make them in the same way that junior engineers do, which means that as a senior engineer it takes me significantly more effort to review. It also makes mistakes that humans don’t, which is even weirder to catch in review.
Takumidesh@lemmy.world 1 month ago
I basically exclusively use LLMs to explain broad concepts I’m unfamiliar with. a contrived example would be ‘what is a component in angular’ or ‘explain to a c# dev how x,y, and z work in rust’ The answers don’t need to be 100% accurate and they provide a nice general jumping point to get specific information.
xavier_berthiaume@jlai.lu 1 month ago
Exactly, I’ve found them most useful to either summarize a text you feed it, or do broad ‘google like’ queries. I don’t trust it with anything beyond that