MEDIA PREVIEW
Overview & result
we almost never test new foundation models but we've been testing this for ~a week @every and it's pretty wild. the kind of things that will be obviously indispensible in 6-12 months it doesn't produce words as output, it produces probabilities. so it can efficiently act as a judge in cases where you'd need a Fable-level model—but in our testing was 25x faster and 600x lower priced excellent vibe check by @hammer_mt on @every: https://every.to/also-true-for-humans/mini-vibe-check-typesafe-s-jev-judged-everything-i-ve-written-in-0-7-seconds?utm_cta_source=home_main_a_3
How Jev fits in the loop
- Ingest real-time application state and relevant contextual parameters
- Format the decision problem as a bounded Choice or Noul schema
- Query Jev to receive a typed probability distribution over the options
- Execute downstream actions or route tasks according to the winning choice
How to reproduce
- Inspect the original showcase and source material at https://x.com/danshipper/status/2099947471518474522
- Verify the bounded prompt and input candidate schema configured for Jev
- Benchmark decision latency and classification accuracy against baseline models
Why this build matters
Demonstrates a real-world, cost-effective implementation of Jev in a specialized agent workflow scenario, replacing expensive generative calls with fast typed decisions.
Limitations
- Task accuracy is bounded by the precision of the defined candidate choices
- Third-party external dependencies and network latency may affect total workflow duration