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 AI & Infrastructure launches Ple, a new benchmark with 29 public tasks and 85 long-horizon tasks across four engineering disciplines. The open competition tests frontier models on real-world projects, revealing all tested models score below 50% on the private test set.
Tap to vote and see what everyone thinks.
Summary by ByteBrief