Post

Nuxt

@nuxt.com

We now run evals to help you know what AI models perform best to write Nuxt code. nuxt.com/evals

26/2/26, 11:22 am9 reposts70 likes

Lukas Trumm

@lukastrumm.com

27 Feb

Awesome! My experience is that for opinionated rules, its still better to mostly include the rules and fine tune them for better results. Might be short, models understand. Here is my own take on evals (focusing on opinionated Vue rules and Claude Code). vue-nuxt-rules.lttr.cz/rule-evals

vue-nuxt-rules.lttr.czRule Evals | Vue & Nuxt RulesA set of opinionated code style rules for Vue and Nuxt based projects.

Nathan Chase

@nathanchase.com

26 Feb

I wonder if this means that: a) Nuxt's error handling docs are insufficient b) The error handling itself is incomplete, or could be better c) Opus just has a hard time dealing with error handling, generally d) All of the above I recently implemented @hrcd.fr's evlog w/ Opus's help. So far so good.

Hugo

@hugorcd.com

27 Feb

Looking at the feedback provided through the docs feedback module, and even being honest, I think the documentation on error handling could clearly be improved, with potentially more concrete examples, etc. 🤔 Btw thanks for using evlog 🙏

Nathan Chase

@nathanchase.com

27 Feb

Perhaps the feedback loop of simply asking Opus (and other models) to look through the existing error handling docs, the error handling code itself, and asking it to make clearer, actionable examples that would better inform the model would be worth trying? Would at least waymark improvements.