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.)
Apple is in early talks with PrismML, a Khosla Ventures-backed Caltech spinout, to shrink AI models for on-device iPhone use. PrismML released compressed versions of Alibaba's Qwen model, reducing it from 54 GB to under 4 GB, enabling all 27 billion parameters to run on an iPhone 15 or newer. The technology uses one to three bits per value, cutting memory 10-15x and speeding responses 6-8x.
Tap to vote and see what everyone thinks.
Summary by ByteBrief