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.)
IBM released Granite 4.2, open reasoning language models in 3B, 8B, and 30B parameter sizes. The models emit chain-of-thought reasoning, include a thinking/non-thinking switch, and a low-effort mode. They were pre-trained on roughly 15 trillion tokens with multi-stage reinforcement learning.
Tap to vote and see what everyone thinks.
Summary by ByteBrief