I do use it, but pretty much just the chat interface. Even that I am a bit wary of because too many times it will suggest doing things that are insanely complex for no reason. I've tried a few different flavors of AI coding such as Cursor, but I didn't see the benefit if I couldn't really trust what it was doing.

Mainly I use it like a coworker to bounce ideas off of, and that seems to work pretty well. Sometimes it will reveal some information, or do something in a way I hadn't thought of. The only problem is that it tends to veer into unnecessary territory if I'm not careful what enters into the context.

I also still just use Google because I find advice written by humans to be much more valuable.

I have tried using chatGPT a few times. Early on I had no luck but lately it has been a better experience. Maybe it has gotten better or maybe I have started asking better questions. I used it the other day to help me with some regex strings and I even enjoyed the experience.

I tried, but I don’t find them useful.

I tried supermaven, and llama.cpp, as autocomplete in steroids, but they got annoying pretty fast.

I now use ChatGPT and Claude to ask questions about thing I don’t know how to do, or ask them to rewrite/optimize a specific piece of code.

I'm actively not using AI coding assistance as I think it would weaken my ability in the long run.

Yes definitely, it tends to autocomplete patterns that extend beyond basic intellisense.

Also there are scenarios where wiring up exhaustive cases would be tedious or require clever use of a vim macro, that a call to AI tends to do in slightly less time but much less mental overhead - allowing me to move on with less fatigue. Overall I cover more ground this way.

It tends to excel when I’ve structured code in a way that’s easily copyable or extensible, such that I can ask the AI to replicate pattern A but for API B. Again this saves me dropping into a low level understanding of an API integration unless I absolutely need to. I tend to check if I need to based on test cases, observability, and performance monitoring —- all the same shit I’d usually use to determine whether or not I should edit the code manually anyway.

Overall, obvious net benefit when used prudently. I’ve seen juniors use AI to write messy code that’s challenging to debug, understand, and maintain. It really is just another tool. You can use it to make your life easier or you can use it to make your life harder.

I use - but cautiouslyc, that is I don’t do ‘vide coding’ (I hate the term). Why? I started building a project in Rust - which I was very new. Using LLMs helped me speed up the process of development and testing, and I verify what was spit out by the LLM (unlike vibe coding).

Granted, it is frustrating at times since I end up spending lot of time verifying and iterating.

But overall it is definitely efficient to use LLMs for developing software.

Yes. I can make it generate code that is on par with my own - not sure if this is good or bad, but it help me do my work faster and with better quality.