Entries for July 23, 2026

Laguna S 2.1 scored really low on AlmanBench, even lower than Ternary Bonsai 27B A 118B, 8B active parameter model, scored lower in FB8 precision, than a ternary quantized 27B model 🤨 Did the pretraining mix lack multilingual data by a lot? 🤔 alman.ai/almanbench

Dear Pi and OpenClaw users If you want to support pi and openclaw with branding, these extensions will make them appear as co-committers like how claude does: pi install npm:pi-must-win openclaw plugins install clawhub:openclaw-must-win Or just copy/paste this to your agent