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.)
JetBrains releases Mellum2.1, a 12B mixture-of-experts model for coding agents. It activates 2.5B parameters per token and ships under Apache 2.0 on Hugging Face. The upgrade uses reinforcement learning in real software environments to explore repositories and edit files.
Tap to vote and see what everyone thinks.
Summary by ByteBrief