Guide · x.com
Together AI fine-tunes a Jev-like classifier on Qwen3.5 4B: about 38,000 questions sampled from eight public datasets, roughly 25 minutes of training, and the tev1 repository that runs it. The $17 is the training job, not the system around it.
Hassan
@nutlope
Sep 23, 2026 · 2.1K likesOpen on X
Diogo Almeida
@CompleteSkeptic
Types Beyond Decisions: box We’re also releasing a new type that is somewhere in the gray area of decisions: a single bounding box. We warned you there’s a reason we call them System One Models! (only on jev-preview)
Guidex.com
Diogo Almeida of TypeSafe on the new Box type: one bounding box per question, somewhere in the grey area of decisions, and only on jev-preview.
Alex Warren
@exrhizo
New @typesafeai Jev capabilities! Some decision models can ask questions about images but can they ask questions with images? 🧵 How to get the most out of the new Jev launch
Guidex.com
Alex Warren’s thread on asking questions with images, not only about them, and how to get the most out of Jev 1.14.
Nathan LeClaire
@dotpem
Here's another JEV TIP in honor of JEVDAY Jev can answer as many questions as you can fit into context in parallel. You can ask hundreds in one call, and since output is free, why not? 100 questions on a 32k token input document: ~$0.00001 per question ~1ms per question
Guidex.com
Nathan LeClaire’s JevDay tip: Jev answers every question that fits in context in parallel. 100 questions on a 32k-token document came to about $0.00001 and about 1 ms per question.