Research & data

Erik Dunteman

github.com

↗

Driving the classifier as a next-token predictor, one token at a time.

hope

github.com

↗

Works out what a Jev confidence score is actually worth.

Marcos Martinez

github.com

↗

A pre-registered audit of how Jev handles Spanish.

Sabrina

@sabrinaesaquino

Jev is now live on the Venice API. Watch it classify 24,000 Hacker News posts into 12 categories in about 2 minutes

OpenRouter

@OpenRouter

1/ Jev, a decision model by @typesafeai, sparked a burst of projects and discussion. We tested it using Ori Eval against popular LLMs on OpenRouter at judging. Jev was >5x faster than the next fastest model, and even its slowest requests beat every other model's median.