I'm one of those really odd beasts that feels some sort of loyalty to Microsoft, so I started out on Copilot and was very reluctant to try Claude Code. But as soon as I did, I figured out what the hype was about. It's just able to work over larger code bases and over longer time horizons than Copilot. The last time I tried Copilot, just to compare, I noticed that it would make some number of tool calls (not even involving tokens!) and then decide, "Nah, that's too many. We're just not going to do any work for a while." It was bizarre. And sometimes it would decide that a given bog-standard tool call (like read a file or something) needed to get my permission every. single. time. I couldn't do anything to convince it otherwise. I eventually gave up. And since then, we've built all our LLM support infrastructure around Claude Code, so it would be painful to go back to anything else.
I don't really like how Claude Code kind of obscures the actual code from you - I guess that's why people keep putting out articles about how certain programmers have absolutely no idea whats going on inside the code.
It's truly more capable but still not capable enough that Im comfortable blindly trusting the output.
That's the big difference for me. I use Github Copilot because I want to see the output and work with it. For people who are fine just shooting a prompt out and getting code back, I'm sure Claude Code is better.
> Claude Code kind of obscures the actual code from you
not sure what you mean, I have vscode open and make code changes in between claude doing its thing. I have had it revert my changes once which was amusing. Not sure why it did that, I've also seen it make the same mistake twice after being told not to.
This is not a problem when you assume the role of an architect and a reviewer and leave the entirety of the coding to Claude Code. You'll pretty much live in the Git Changes view of your favorite IDE leaving feedback for Claude Code and staging what it managed to get right so far. I guess there is a leap of faith to make because if you don't go all the way and you try to code together with Claude Code, it will mess with your stuff and undo a lot of it and it's just frustrating and not optimal. But if you remove yourself from the loop completely, then indeed you'll have no idea what's going on. There still needs to be a human in the loop, and in the right part of it, otherwise you're just vibe coding garbage.
What I don't understand is why so few people talk about AugmentCode, it uses claude (and others) but builds context of your project and tends to understand your repos better.
What I wish for would be a lego technics creative box with motors etc... Thats closer to what I had as a kid and I built a lot of fun things with that. Never liked the basic legos that much though
That's something I've run into myself. I just recently finished the Enterprise Lego set, and it was fun to build... but I doubt if I will ever take it apart and rebuild it. There were 30 bags in that set, and I don't much fancy the prospect of trying to sift through all the pieces at once rebuilding the thing.
when I was a kid I wanted some of the specialised sets simply because they had exciting new pieces like windshields, gears, dish antennas, etc. I don't think I ever made the actual thing the set was intended for, I just wanted to add new pieces to my lego bin.
Everyone’s got a basket of things they can love or hate about this place when they’re in the mood to love or to hate. That’s something to love, I think.
reply