I have a bunch of open tasks on my GH repos, so I tried asking ChatGPT and Claude to write a card-based web UI that showed some random open issues.
ChatGPT gave me something that worked, but the Claude mock-ups look better (and render inline!).
miniblog.
Related Posts
I find that I'm choosing AI tools based on the quality of the harness rather than the model.
For example, I'm using Claude Code Web because its model of remote VMs is extremely convenient. I'm using Perplexity because it's tuned really well for web searches.
Anthropic used Claude to write a C compiler in Rust (CCC). I've really enjoyed following the discussion.
The initial post shows how they wrote the harness with GCC as an oracle and a prompt specifying a design using SSA. The author has clear domain expertise.
https://www.anthropic.com/engineering/building-c-compiler
LLMs are great at style transfer, and this works surprisingly well for syntactic transformations too.
I rewrote a small website's EJS templates to 1500 LOC of TSX with a oneshot in Claude. It took ~12 minutes, but it just worked.
(TSX seems nicer than EJS for static analysis.)