author:csgbwk
· 5 artifacts, sorted by favorites. · open in search — combine tags, sort, filter by date →
- @csgbwk 2026-06-25 — I'm pretty sure a GLM5.2 LoRA'd on an internal dataset is by far the best model in the world right now and would not cos ♥21
- @csgbwk 2026-10-06 — Getting there! Not two years behind the frontier anymore! Rooting for mistral! Will definitely spend a few tokens! ♥1
- @csgbwk 2026-09-08 — I suspect a reason mistral fell is that they don't benchmaxx. Mistral 3.5 medium is honestly as useful as gemini 3.5 fla ♥0
- @csgbwk 2026-08-22 — There's a non zero chance Ox Alpha is both gemini and a benchmaxxed GLM 5.2 finetune ♥0
- @csgbwk 2026-08-04 — What's the state of things for TML by @thinkymachines ? I'd like to use it for a voice interaction project but i can't f ♥0