←back to thread

What makes Claude Code so damn good

(minusx.ai)
469 points samuelstros | 1 comments | 23 Aug 25 19:07 UTC | HN request time: 0.222s | source
Show context
gervwyk ◴[23 Aug 25 20:12 UTC] No.44998759[source]▶
We’re considering building a coding agent for Lowdefy[1], a framework that lets you build web apps with YAML config.

For those who’ve built coding agents: do you think LLMs are better suited for generating structured config vs. raw code?

My theory is that agents producing valid YAML/JSON schemas could be more reliable than code generation. The output is constrained, easier to validate, and when it breaks, you can actually debug it.

I keep seeing people creating apps with vibe coder tools but then get stuck when they need to modify the generated code.

Curious if others think config-based approaches are more practical for AI-assisted development.

[1] https://github.com/lowdefy/lowdefy

replies(6): >>44998775 #>>44998776 #>>44998799 #>>44998886 #>>45004566 #>>45007266 #
1. riwsky ◴[24 Aug 25 20:01 UTC] No.45007266[source]▶
> For those who’ve built coding agents: do you think LLMs are better suited for generating structured config vs. raw code?

Raw code. Use case was configuring a mapping of health data JSON from heterogeneous sources to a standard (also JSON) format. Initial prototype was a YAML DSL, based on the same theory as yours. LLMs had difficulty using the DSL’s semantics correctly, or even getting its syntax (not YAML-level syntax, but the schema: nesting levels for different constructs, and so on). It’s possible that better error loops or something would have cracked it, but a second prototype generating jq worked so much better out of the box that we basically never looked back.