jevIMAGE
Hands-on with the Jev API: declare output shape like DSPy
Given access to Typesafe AI's Jev, the author finds the API works like DSPy with instructions, context, and a declared output shape, filling JSON fields like a mask prediction model and acting as a very fast generic classifier.
AVB
@neural_avbArchived 2026.09.18Originally posted 2026.09.17
AVB @neural_avbOriginally posted 2026.09.17
Just got access to Typesafe AI's new Jev model The API is similar to how I would use DSPy -> some instructions, context as a string, and DECLARE the desired shape of the output. The API runs some kinda JSON predictor and returns the structured output. Feels similar to mask prediction models where the JSON schema is fixed and the model predicts the missing values. A superfast generic classifier of things
x.com/neural_avb/status/2100467971479286135Archived 2026.09.18 10:16