CalibratedDecisions.

Repo · Benchmarks & research

Jevlet

From-scratch research reconstruction of a Jev-like System One decision model (typed Noul/Choice/Score → probabilities, no text generation) plus a…

Open github.com ↗

From the repository

Jevlet: a small, calibrated System-One decision model (typed Noul/Choice/Score questions in, probabilities over live options out, no text generation) driving an always-on Windows command palette. Research reconstruction of TypeSafe's Jev idea.

automationbgecalibrationcommand-palettedecision-modeldeep-learningdesktop-assistantgoogle-colabhuggingfaceintent-classificationmachine-learningnlpproductivitypytorchresearchslot-fillingsystem-onetransformersuncertaintywindows

How builders describe it

From-scratch research reconstruction of a Jev-like System One decision model (typed Noul/Choice/Score → probabilities, no text generation) plus a Windows command-palette daily driver.

The decision Jev makes

Benchmark questions with known answers, to check accuracy and confidence.

Where it fits

Head-to-head tests, calibration studies and independent research into how well Jev decides, how fast, and at what cost. All 355 benchmarks & research projects →

Related projects