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.)
Google introduces the LiteRT Tensor API, a lightweight C++ tool for building machine learning models on devices. It enables cross-platform portability across CPU, GPU, and NPU hardware without rewrites. A coding agent optimized the SAM 2 model to reach over 30 frames per second at 512x512 resolution on WebGPU, beating Apple MLX performance by 1.5x on a MacBook Pro.
Tap to vote and see what everyone thinks.
Summary by ByteBrief