Ask HN: Is Claude Code good enough already?
I've started to have a sneaking suspicion that claude code has already reached a key level of what I will call 'quite amazing'. When Google released Gemini 3 and Antigravity, I tried them out. They're good, great even. But, as a software dev, I'm back to trusty Claude Code. I really like it. More than anything, I really hope it can stay where it's at with performance and price and become profitable so that I'm allowed to keep it!
I don't particularly care about SWE bench or how much higher the next model scores on it. Perhaps that's not very futurist of me.
How do you feel about this? Depending what you want to do, what's your workflow, and everything.
Personally, I use a mixture of Claude Code and Cursors - vide https://quesma.com/blog/claude-skills-not-antigravity/ At this point, I'm not so concerned about the interface (claude code vs github copilot, etc, etc.) Sometimes I need to use one over the other because of...reasons. But I do seem to be coming back to the Anthropic models in particular. My rule of thumb is turning out to be: 1)How long is this taking?
2)Was it the right solution? The first is pretty easy to get a feel for. The second is also a feeling I'm developing over time, but I am starting to trust the Anthropic models for all my coding.