Similar. I regularly use Github copilot (with claude models sometimes) and it works amazingly. But I see some who struggle with them. I have sort of learned to talk to it, understand what it is generating, and routinely use to generate fixes, whole features, etc. much much faster than I could before.
I’ve found copilot to generate worse code, and the editor integrations to be unusable (lets insert this block of code at the wrong place in the file for example), but overall for it to do the right thing enough that I can patch it. I’ve found Claude code just goes mad and gets stuck in a loop and I need to pull it out and figure out where in the hundreds of lines of code it’s generates in the last few minutes it’s gone so wrong.
