TYPESAFE RELEASED A MODEL THAT DOESN'T GENERATE TEXT, AND

Replaced six of eight decisions in an agent loop with Jev calls, keeping only planning steps on a chat model to cut latency and cost.

The original post

TYPESAFE RELEASED A MODEL THAT DOESN'T GENERATE TEXT, AND IT BREAKS THE COST FLOOR OF THE AGENT LOOP

jev is what they call a system one model. you send it a state and a set of questions, it returns typed answers with probabilities. no tokens, no sampling, no sequential decoding.

route → decide → guard → run tool → observe → done?

they report 20-200x faster inference and 40-400x lower cost than comparable llms on classification tasks. every question in a request is evaluated in parallel, so adding questions barely moves latency.

in a two-turn loop that means eight decisions. the two that need a plan still go to a chat model. the other six - pick a model, screen a tool call, check if the task is done - cost 0.06s combined.

the takeaway is simple: stop paying generation prices for choices. most of what an agent decides is a pick, a score or a yes/no.

Quoted post

S

@sydneyrunkle468.6K views

source

Engagement when collected

Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.