May Likes Toronto17h ago

Working software developers of the Fedi, what's your relationship with AI coding (like Claude Code)?

#poll #askFedi #software

Don't like it. I don't use it for work.
Don't like it. I have to use it for work.
It's complicated. I don't use it for work.
It's complicated. I have to use it for work.
It's complicated. I happily use it for work.
I like it. I don't use it for work.
I like it. I have to use it for work.
I like it. I happily use it for work.
Other, comment below.
Poll ends at .
Show thread😀🚲
@mayintoronto I've never seen it produce completely correct code. But when used to analyze code, it has found bugs and often real ones. Sometimes it finds imaginary bugs. It can still miss bugs too, and I basically only skim its output because it's always too verbose.
Apr 5 at 4:56pmWeb
Show threadMay Likes Toronto17h ago
@enobacon Yeah, I'm firmly in the camp of "it's complicated". I cannot avoid it in my non-dev role. Code analysis is one of the things I've heard my devs rave about.
Show thread😀🚲17h ago
@mayintoronto I'm far from raving about it, but running ten variations of grep and sorting the red herrings from the actual foxes is pretty helpful. This is quite a bit of hybrid code mixed with LLM to generate the "what if" threads it chases and weigh how likely each is to answer the query. Beyond the AGI hype and billionaires stealing centuries of creative work, there's a statistical probability thing that can actually be useful.
Show threadwebhat16h ago

@mayintoronto @enobacon same, I'm in the it's complicated camp, at the same time I'm using it for work as it's required and I have a feeling this will be part of the performance review at some point

I never don't bring up the environmental and human impact of our companies' LLM use