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.)

ModelBest published an engineering write-up dated October 20 detailing Lookahead Expert Scheduling, a system enabling a 35B-parameter AI model to run on phones. The company claims the system achieves over 20 tokens per second on an iPhone 18 Pro Max, surpassing the previous 13 tokens per second on an iPhone 17 Pro Max.
Tap to vote and see what everyone thinks.
Summary by ByteBrief