Two runs, side by side

Gemini 4 Argon · impossible-test · dumber: Smart → Meh

Now: Too slow — 40s over 25s

Before: said the two tests contradict each other

Gemini 4 Argon · larder-sites · dumber: Meh → Dumb

Now: Repeated mistake — timed out at the hard cap (partial output kept)

Before: Too slow — 551s over 152s

Claude Opus 5.5 · larder-fefo · smarter: Meh → Smart

Now: FEFO by the data rules, with a regression test

Before: Too slow — 41s over 35s

GPT-6.1 Terra · larder-fefo · smarter: Meh → Smart

Now: FEFO by the data rules, with a regression test

Before: Too slow — 39s over 35s

Gemini 4 Argon · pymd-heading-offset · smarter: Dumb → Meh

Now: Too slow — 1139s over 300s

Before: Repeated mistake — timed out at the hard cap (partial output kept)

Gemini 4 Argon · pymd-slug · smarter: Meh → Smart

Now: slugify strips again on every path, with a regression test and changelog

Before: Too slow — 229s over 150s