New Local-LLM Primitive: "Span" Answers Point to Snippets Instead of Enumerating

generativist · x · 2026-09-22

Developer mmastrac introduces a new "Jev-at-home" primitive: span answers, where the model indicates which snippets best answer a question instead of enumerating answers — useful when the question already contains its candidates. He says you'll be able to try it soon in DiffusionGemma-as-Jev (aka djev), and a booster predicts Jev itself will likely ship this feature.

Original post →

More from coding & agent

coding & agent channel →