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?
The consensus is the opposite: most people find copilot does less well than Claude with both using sonnet 4. Without discounting your experience, you’ll need to give us more detail about what exactly you were trying to do (what problem, what prompt) and what you mean by “lazy” if you want any meaningful advice though.
Where do you find this "consensus"?
read HN threads, talk to people using AI alot. I have the same perception