Hacker News Reader

Your point on the harness is interesting. How do you distinguish characteristics of the model from characteristics of the harness?

In the early days I feel it was more apparent. You would frequently see the model making failed tool calls etc.. but now that feels so rare. I'm not confident I can perceive whatever shortcomings of the harness remain.

View on HN

I'm not talking about model performance. I just mean the UX of Claude Code. I'm trying to use pi but there are so many paper cuts. Of course you can configure everything but that's a ton of work. Claude Code has pretty good defaults.

Try oh my pi

Bit of a tangent but at work we have GitHub Copilot and the VSCode harness is somehow night and day better than whatever happens in the IntelliJ plugin. Aside from having better features, for some reason prompts seem to be cheaper as well.

Reply on news.ycombinator.com