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.)
Block released Dessa, a new voice model running locally on a single NVIDIA GPU or a MacBook M4 Max. Trained fully on human speech, the model features built-in emotion and runs without text pipelines. Currently, there is no public access to Dessa as Block calls for safety researchers to test the system before wider deployment.
Tap to vote and see what everyone thinks.
Summary by ByteBrief