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.)
1 story in the last 7 days
The latest sample-efficiency news, distilled by AI into sharp ~100-word summaries. ByteBrief tracks sample-efficiency across dozens of tech sources and brings you only what matters, updated hourly. Tap any story for the full brief, or open the original source.
A small transformer trained from scratch in 1.5 hours on a 5090 scores 44% on ARC-AGI-1, matching TRM/HRM at 67 cents. The supervised approach skips input tokens, adds filtered ARC-2 data, and uses NorMuon, 3D RoPE, and per-task embeddings. Code is open source.
Summaries by ByteBrief