zlacker

I don't get why people want the AI right in their editor. In another windows inside the editor, fine, but not inline with code I'm writing. It's super distracting to have AI auto complete pop up at random all the time. As always, typing speed, or speed at generating raw code, is not the bottleneck in programming. The crux remains design, in which case having the LLM on the side is just fine (if you use it for that).

There are some niceties about inline completion (like spelling out a log message that's obvious from the surrounding code) but I don't get the hype much beyond that.

Maybe I'm missing some feature though ...

>>D4ckar+(OP)
Have you tried it recently?

AI autocomplete is the best thing I've experienced in developer experience in my career since git won over subversion.

I don't use LLM code prompting, but autocomplete is my jam. It's getting things right 90% of the time when I'm plumbing fields or refactoring. It makes life so much more pleasurable, and I say that as someone who is already using a statically typed language with robust IDE refactoring capabilities.

It's absolutely made me more productive.

>>echelo+O
I am happy with Copilot with VSCode..I do not think so, I would need to let AI generate the entire code. Even if I need, I copy/paste from Claude/GPT

>>D4ckar+(OP)
If you have tried the completions in copilot, you are right. They are complete garbage.

Windsurfs on the other hand are much better. The only issue is that windsurf is super aggressive about them, but it is able to do do things like "the user made a change on this line, he most likely also want to make the change here".