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.)

Newer versions of Anthropic's Claude models perform worse at tool calls than earlier versions. The regression affects the models' ability to correctly invoke external functions and APIs, reducing reliability for developers relying on structured tool use.
Tap to vote and see what everyone thinks.
Summary by ByteBrief