CHOOSEDevtools & code

Jev Outcome Correction

Aaron Horne@ahorne

Play video

Original post ↗

This project uses Jev to correct errors in a Replit project, significantly reducing the number of possible outcomes that need manual attention.

Related builds

Jev Judgment Model Evaluation

Jev is a judgment model from TypeSafe AI that provides probabilities and confidence scores for typed questions based on a given state, designed to function as a non-acting governance layer.

Marquise@marquisehurtt

403 views on XJev score 80

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

95 views on XJev score 76