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.)
Supabase open sourced supabase/evals, a benchmark framework testing AI coding agents like Claude Code, Codex, and OpenCode on real Supabase tasks. Skills boosted scores, with Sonnet 5 rising from 78% to 100%. Results are published at supabase.com/evals.
Tap to vote and see what everyone thinks.
Summary by ByteBrief