←back to thread

What makes Claude Code so damn good

(minusx.ai)
469 points samuelstros | 1 comments | 23 Aug 25 19:07 UTC | HN request time: 0.216s | source
Show context
syntaxing ◴[23 Aug 25 20:00 UTC] No.44998675[source]▶
I don’t know if I’m doing something wrong. I was using Sonnet 4 with GitHub Copilot. Recently a week ago switched to Claude Code. I find GitHub Copilot solves problem and bugs way better than Claude Code. For some reason, Claude Code seems very lazy. Has anyone experience something similar?
replies(5): >>44998728 #>>44998732 #>>44998821 #>>44998958 #>>45001414 #
1. cosmic_cheese ◴[23 Aug 25 20:08 UTC] No.44998728[source]▶
I haven’t tried other LLMs but have a fair amount of experience with Claude Code, and there definitely times when you have to be explicit about the route you want it to take and tell it to not take shortcuts.

It’s not consistent, though. I haven’t figured out what they are but it feels like there are circumstances where it’s more prone to doing ugly hacky things.