ByteBrief
We're a portrait publication through and through. Turn your phone back and your briefing picks up right where you left it.
(We tried widescreen once. It wasn't us.)
A 9B Jev-like model called Jeeves, trained with SFT and CISPO, reasons before deciding and beats Kev-9B and Jev on unseen test data (0.889 vs 0.822 and 0.857) and JevBench public tiers (0.935 vs 0.866). It supports yes/no, multiple-choice, and rating questions via a Jev-compatible API, running on one H100.
Tap to vote and see what everyone thinks.
Summary by ByteBrief