The new release lets users turn any text or vision LLM into a Jev‑style decision model, boosting accuracy up to 80%, and adds native ComfyUI diffusion models.
NoteBy OossaPublished by Oossa: Last updated: 1 min read
Unsloth released version 0.1.904‑beta on 7 October 2026. The update introduces a decision‑model feature that can convert any text or vision LLM into a Jev‑style model, raising decision accuracy from about 30 % to 80 %. It also adds native support for ComfyUI diffusion models, faster INT8 ConvRot generation, and a more stable desktop browser.
Developers can now build higher‑accuracy AI decision tools and run diffusion models directly in Unsloth without extra pipelines.
Models
The company’s new three‑agent Claude‑based reviewer found 73.43% of core‑claim errors, far above the previous best of 14.81%.
Models
Mistral's new trillion‑parameter model scores 38 on an independent index, but costs more per task than competing open models.
Models
OpenAI reported two influence campaigns that used AI‑generated content to plant false stories in real media and blocked the involved accounts.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
