miniblog.

I've been impressed with code written by Fable in my testing: Difftastic: found small optimisations in a hot loop I'd already profiled extensively. Helped me prototype Dijkstra to A* too (hard to find a good heuristic). Garden: Found some real bugs in my simplistic typechecker.

I've had good results by prompting an LLM "review your changes" in the same session when I don't like the initial output. I'm surprised this is effective: I would think it's redundant when you're running with a high effort setting.

I've never seen a good design philosophy on how to sort compiler errors for the best UX. Do you order by line, or by severity? Do you put the most actionable at the end (because that's most visible when the terminal scrolls) or at the beginning?