SiftRank adds Jev as an LLM ranker to sift needles from data haystacks
dyn___ · x · 2026-09-20
SiftRank, an open-source tool that uses LLMs to semantically rank and surface relevant items from large datasets, now supports Jev as an underlying ranker alongside OpenAI-compatible Chat Completions APIs (--provider jev). It targets cases where the signal can't be expressed as regex and won't fit an agent's context window, ranking prose, files, JSON, code, tickets, and more. It also ships an agent skill so agents can retrieve the most relevant items on the fly.
More from coding & agent
- Claude Skill turns an image's buildings into resizable Three.js models — jasonkneen · 2026-09-20
- Fuzzing vs property-based testing: the terms are splitting — exploration vs assertion — blaizedsouza · 2026-09-20
- Software factory take: LLMs may generate, but never specify or verify — blaizedsouza · 2026-09-20
- Jev as an NSFW prompt filter: 93% on CSAM evals, sub-cent cost, and where thresholds bite — Murky_Ad8671 · 2026-09-20
- "A heuristic cannot certify a heuristic": why software-factory orchestration thinking is wrong — blaizedsouza · 2026-09-20
- Reality check: normies' AI views are detached — top results go to those who delegate hardest — Revolutionalredstone · 2026-09-20