Onur Solmaz blog

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? 🤔 https://t.co/OGBSm0LYlh

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

Ran Laguna S 2.1 *theoretical* (not measured) upper bound calculations for the DGX spark poolside/Laguna-S-2.1-NVFP4 - max ~25 tok/s single session. if you are willing to go down to 12 tok/s, you can have 4 sessions in parallel vcruz305/Laguna-S-2.1-GGUF (IQ1_S) - max ~74 tok/s single session. theoretical 5x20 tok/s = 100 tok/s aggregate upper bound Calculated assuming no spe...

Repos: https://t.co/WMApSZXX16 https://t.co/qkoYq4A0r5

There is an inherent unfairness in this industry If you are Anthropic, Cursor or another billion dollar company, you can do growth hacks and guerrilla marketing techniques like putting your brand into every commit of a user, and get away with it But if a tool like pi, opencode or even say vim or emacs tried to do that, they would be boo'ed Like, it happened to @herdrdev recen...