Re-Ranking Context with Explicit Feedback, Without Letting It Take Over
The previous post covered TokenCap's local learning ledger: a file of explicit judgments about context packs. This one covers what reads it. tokencap ask " " --adaptive uses that evidence to re-rank the files retrieval found. It is opt-in, it is bounded, and it explains itself. Running it tokencap…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-11-17 12:09 · DEV Community — AI
Re-Ranking Context with Explicit Feedback, Without Letting It Take Over