Article · by Kitsuno

Laya in shadow, next to Jev on every request

Kitsuno trains an open model to replace Jev in production.

Kitsuno sent its production requests to Laya as well as Jev. On the test set built that day, the untrained Laya answered 44 percent of the questions correctly and Jev answered 94 percent. The write-up covers the eight days since: how the team taught Laya its questions, where it trained, and how it now runs next to Jev on every real request. Since 23 September, Jev has answered 35,812 logged calls for Kitsuno, with 76 million input tokens, for USD 3.68 in total.

Open the source

More like this

Dan Shipper

@danshipper

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