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.

My $2/month VPS has stopped and can't even boot, so I've switched provider. It seems like most server providers don't want to offer <$5 machines, and I imagine it's hard to make money at the low end. Several providers require a one-off setup fee too.

After further playing with my LLM project, I'm surprised how hard it is to tune with system prompts. My agent kept saying "obviously" even though my prompt said "helpful, professional". Eventually I found that a "courteous" prompt gets "of course" which is better but not ideal.