What makes Claude Code so damn good

I think it’s just that the base model is good at real world coding tasks - as opposed to the types of coding tasks in the common benchmarks.

If you use GitHub Copilot - which has its own system level prompts - you can hotswap between models, and Claude outperforms OpenAI’s and Google’s models by such a large margin that the others are functionally useless in comparison.

Anthropic has opportunities to optimize their models / prompts during reinforcement learning, so the advice from the article to stay close to what works in Claude code is valid and probably has more applicability for Anthropic models than applying the same techniques to others.

With a subscription plan, Anthropic is highly incentivized to be efficient in their loops beyond just making it a better experience for users.

I read all the praise about Claude Code, tried it for a month and was very disappointed. For me it doesn't work any better than Cursor's sidebar and has worse UX on top. I wonder if I am doing something wrong because it just makes lots of stupid mistakes when coding for me, in two different code bases.

It's not just the base model

Try using opus with cline in vs code. Then use Claude code.

I don't know the best way to quantify the differences, but I know I get more done in CC.

But is it a game changer vs CoPilot in Agent mode with Claude 4 Sonnet?

Because it's twice the price and doesn't even have a trial.

I feel like if it were a game changer, like Cursor once was vs Ask mode with GPT, it would be worth it, but CoPilot has come a long way and the only up-to-date comparisons I've read point to it being marginally better or the same, but twice the price.

I'll suggest giving it another shot. It really is a game changer (I can't tell what you're doing wrong, but in a few people I've seen it has been about doing a psychological switch. I wrote about it a bit here - https://mnvr.in/beginners-mind, sharing in case it helps you see how you might approach it differently)