Onur Solmaz blog

Note: this post is AI-assisted. It was written with Claude Fable 5. How do you depend on code you intend to modify? Package managers assume you never touch the installed files. Forking gives you full control at the cost of maintaining a second repository.

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/OGB

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

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 (IQ

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

I created a semi-automated setup for ingesting X posts into my blog, and it works pretty well! I own my posts on X now Posts are scraped while I browse X using...

Explorations in software, agentic systems, math, languages and more.

Explorations in software, agentic systems, math, languages and more.