AI ideas tested on real systems: measured results, code included.
- [Part 1/2] A production LLM's weights edited almost-by-hand. It worked. A logistic regression did the same job better.
2026-11-14 — Weight-space programming tested on a 26B production LLM judge: a direct weight edit vs a linear probe vs a better prompt, measured. - [Part 2/2] Prompt optimization for an LLM judge: how to see how much accuracy your prompt leaves unused, and when to stop
2026-11-14 — A linear probe on the model's last hidden state shows how much accuracy an LLM judge's prompt leaves unused, and when prompt optimisation can stop.