CHOOSEAgents & automation

Jev by TypeSafe AI

Meng Li@dlimeng192048

34 views on X · does not affect score

Jev is a System One model designed for structured judgments, accepting context and a scoped question to provide program-ready answers with probabilities, including outputs like Choice, Noul, and Score, and supporting runtime natural language labels without retraining.

TakeOutputs include Choice, Noul, and Score.

Pattern↑ State to typed decisions for software

Related builds

Jev Decision Model

Jev is a typed decision model that returns a probability for a given state (question, answer, evidence) instead of generating prose or structured data, making it faster and cheaper than traditional AI judges.

Jose Luis Latorre | #MVP | #K6 | @DotNetZurich@joslat

40 views on XJev score 79

Jev Model Asymmetry Analysis

This project analyzes the Jev model's behavior, revealing that natural language wording induces a significant conviction asymmetry between buy and sell sides, while the model itself is symmetric when presented with symmetric prompts.

Dan Holzrichter@dholzric

83 views on XJev score 79

TypeSafe Computer Use

This project enables a Mac to achieve plain-English goals by combining OCR and the Accessibility tree to drive actions, avoiding large model loops for screenshots.

Yash Chaudhary@YashChaudhary

4 views on XJev score 78

Jev Decision Model Evaluation

Jev, a decision model from TypeSafe, was tested on standard AI problems, answering structured questions with probabilities and performing comparably to or better than other models on single-step tasks, but struggled with sequential reasoning without state information.

Nikhil Deshpande@nikhdesh

94 views on XJev score 76