Updated

Desk

People

62 people whose public posts or write-ups became stories on this desk. Handles are how they posted. For how a story gets on the list, see method.

Diogo Almeida

@CompleteSkeptic

TypeSafe CEO. Launch thread, Jevons-paradox posts, and the official System One write-up. On September 22 he said new signups are suspended so the team can sleep, and he asked whether Exa's web-context demo was real.

Launch System One Jevons Signups paused Exa demo

Sasha Sheng

@hackgoofer

TypeSafe cofounder. Posted that Jev 1.13 is still too slow, too expensive, and too dumb, and pointed at the jaggedness docs.

Jaggedness

Gregor Zunic

@gregpr07

Browser Use. The 7-second Google Flights clip and jev-ultrafast.

Flights

Ashutosh Mathore

@ashutoshftw

200-piece Tetris bake-off: Jev 9,200 points at about 300 ms per move, 0 illegal landings, against Haiku and Gemini.

Tetris

Kyle Jeong and Joey Kudish

@kylejeong / @jkudish

Stagehand computer use, plus jev-browser.

Stagehand

Tamara Tran

@tamarajtran

Compaction by scoring tool calls instead of summarizing them.

Compaction 30 tasks

AstroHan

@AstroHanRay

30 FrontierHarness tasks with a Jev context filter: 25/30 versus 22/30. meriyah 49/49 versus 0/49.

30 tasks

Luke Kranz

@lkkrnz

Jevflake, a dbt package that calls Jev from Snowflake SQL. Version 0.1, one live account.

Jevflake

mizutani

@m_mizutani

semgate, a Go HTTP middleware, plus Injection Range on Cloud Run.

semgate

Nandha Kishor M

Convai Innovations

Laya, an Apache 2.0 typed-decision engine. JevBench 70.1. Author table trails published Jev on Banking77.

Laya

Yusuke Wada

yusukebe

Hono semantic router on Cloudflare Workers AI, then a warning not to let Jev write the reply.

Hono

Ryan Vogel

@ryanvogel

1,500 personal emails on a livestream. Sample size is in the post. Accuracy is not.

1,500 emails

Jarrod Watts

@jarrodwatts

jev-trader on Monad/Kuru. Defaults to a mock model and dry-run without PRIVATE_KEY.

Trader

Mike Taylor

Every

777 writing judgments in under 0.7 seconds, then a 12-passage defect check against Claude Fable 5.1.

Every

Jackson Clark

@HacksonClark

SREGym-Lite: Codex at 20/50 without Jev, 24/50 with jev_plan and jev_submit.

SREGym-Lite

Elvis

@elvissun

News Desk Dealer: 384 headlines in 24.9 seconds at $0.19. Opus 5 finished four.

384 headlines

Mahesh Sathiamoorthy

@madiator

Bespoke Labs. Nimble 9B LoRA, 90.12% versus Jev 93.21% on 324 synthetic labels.

Nimble

Hemant

@heman10x

Verdict, a 151M encoder that runs in a browser tab. On 337 TypeSafe public cases: 48.1% versus Jev 90.8%. JevBench listed the 1.4 engine at 72.5.

Nimble JevBench

Justin Schroeder

@jpschroeder

JevPilot, a Three.js driving sim that asks Jev which sampled path to take.

JevPilot

Michael Malis

@mmalisper

Postgres JOB overlay. Join-order alone was slower. Hybrid override: 12% geomean.

Postgres

Nikhil Mudholkar

@nikhilmudholkar

Bryo. 1,565 supplier emails, Jev 96.4% versus two Gemini models a point or two higher.

Bryo

Charly Poly

@whereischarly

Banking77 against open encoders. Jev won macro-F1 and lost Expected Calibration Error.

Encoders

Aman Kumar

@onlyoneaman

About 16,000 calls, four public sets, then production page gates. Filter, not classifier.

Filter

Logan Markewich

@LoganMarkewich

jeff, a local /v1/systemone server on GLiFormer, with a 1,600-item table against live Jev.

jeff

GitHub Next

@GitHubNext

LocalJev, a prompted Bun stand-in for the System One API, plus a 1,200-request bake-off.

LocalJev

Josh C. Simmons

@drjoshcsimmons

Jev macOS Loop. Six native GUI tasks passed. Finder sorted nine files in 7.39 seconds.

macOS Loop

Sam Saffron

@samsaffron

term-llm pull request 1150: Jev as a hidden control plane for GPT Live, shadow mode on.

term-llm

Jake Gwon

@jake_gwon

jevis, a Flutter integration-test package that ranks registered widget actions.

Jevis

Florian S

@airesearch12

JevBench. 534 decisions, four axes, geometric mean. Jev 1.13.0 at 75.4 on v1.2.8; classifier.dev's fast tier is Jev behind another API.

JevBench djev SimpleJev

Daniel Shea and Seán Roche

LangChain

Jev as a judge on five frozen weather-agent traces. 500 matching pass/fail labels, $0.34 against Claude's $28.17.

Judge

Jason Lemkin

@jasonlk

600 SaaStr Connect judgments. 90× cheaper than Sonnet, 32% false admissions on 148 negatives.

SaaStr

Theodore Lee

@theoleecj

SemIf, formerly OpenJev. Qwen3.5-4B logit readout. JevBench 74.7 versus Jev 75.4.

SemIf JevBench

Jared Palmer

@jaredpalmer

Kev, an Apache 2.0 family of Jev-like models on Qwen. Author new-source table: Kev-8B 79.6% versus Jev 85.7%. JevBench listed kev 0.6B at 66.7.

Kev

LiteLLM

@LiteLLM

TypeSafe pass-through on the proxy, plus a Jev compaction guardrail that drops older tool results below 0.2.

LiteLLM

Matt Mastracci

@mmastrac

DiffusionGemma-as-Jev clips, including phone-camera vision. JevBench tags him on the djev row; the hosted API is Maisa's djev.dev.

djev

Featherless AI

@FeatherlessAI

SimpleJev, an Apache 2.0 classifier server that reads next-token logits. JevBench listed Qwen3.8-27B at 67.3.

SimpleJev

jaidev

@hijaidev

Posted jevctl, a friend's npm CLI wrapping Jev as shell commands. Repo is Nasrallah-AL/jev-cli.

jevctl

Jerry Liu

@jerryjliu0

LlamaIndex cofounder and CEO. DocJev classifies and splits PDFs with local LiteParse and hosted Jev. Author table: 40/40 classify, 7/8 split, 5.73x / 6.45x versus Luna.

DocJev

TypeSafe AI

@typesafeai

Posted the September 21 API and console incident, then We are back. On September 22 the same account paused new signups and said existing signups continue.

No waitlist Outage Signups paused

khmuhtadin

@khmuhtadinn

n8n-nodes-jev-classification, an MIT community node with one output per category plus Needs Review.

n8n

Prasanth J

@prasanth_j

Native C++ DuckDB extension that batches Jev over SQL rows. Live Choice run: 2,049 synthetic rows in 0.887 s, cached replay 28.6 ms.

duckdb-jev

Kyle McLaren

@kylemclaren

jevsearch, a shadcn site-search block that re-ranks keyword hits with Jev. Author table: 83% Hit@1 versus 41% on the keyword pass.

jevsearch

RZ

@snoopydev99

Recorded 100-case security triage of Jev, Terra, and Opus. Balanced accuracy 65.3% / 75.1% / 91.2%. Repo Robertzu43/system-one-security-triage.

Security triage

Zefan Cai

@Zefan_Cai

PhD student at UW-Madison. Open-Jev, Qwen3.5 LoRA plus a decision head. On 231 public JevBench tasks the released 9B checkpoint is 179/231 against Jev 200/231.

Open-Jev

Khaled Eltokhy

@eltokh7

jsort, an MIT pairwise ranker. CommonLit r 0.824 at $0.046. Package author in keltokhy/jsort.

jsort

Joe Weisenthal

@TheStalwart

Posted a JSort rescore of 4,005 FOMC speeches and statements. The repo's published Fed check is 95 opening statements.

jsort

Ben Sabic

Vercel

Author of the form-router guide. The September 21 announcement is the @aisdk post. Jev keeps the destination at confidence 0.95. Below that, Luna Fast decides from the same submission.

Form router

MotherDuck

@motherduck

Shipped prompt_jev(), a SQL function on paid plans. On 100,000 AG News training rows the published table is 89% accuracy, 2,484 rows/s, $0.50, 40 seconds.

prompt_jev

Chirag

@chirag

Posted llamacpp-jev. The repo is NakliTechie/llamacpp-jev, MIT. It serves /v1/systemone from an unmodified llama-server. Fresh-image median on an idle M4 Pro is 526 ms.

llamacpp-jev

syumai

@__syumai

jevyoumean, MIT, command jym. One Jev Choice against a CLI's help when the subcommand is unknown. Valid commands do not call the API.

jym

Vini Lana

@oviniciuslana

jev-gateway, MIT npm proxy for Codex, Claude Code, OpenCode, and Gemini CLI. Chess-engine bench: Astra and Sol bug-fix output -57%. Opus 5's feature task was slower.

jev-gateway

Christian Tzolov

spring.io

Wrote the September 21 Spring blog on spring-ai-community/spring-ai-typesafe. Three-question ticket call, 310 ms median on his laptop. The blog says 0.1.0 is on Maven Central.

Spring AI

andreapn

use-agent-os

GitHub user andreapn opened AgentOS pull request 3316, the opt-in Jev Pilot Router strategy. The announcement chart is 0.901 accuracy against the local classifier at 0.355, on 121 labeled turns.

Pilot Router

0xNeoArch

@0xNeoArch

Posted mizorewww/laya-mlx. The README's M3 Max median is 13.42 ms for the 421M checkpoint. Selected answers matched upstream Laya on 63 of 63 validation questions.

laya-mlx

maxli

@maxlibin

jev-rubiks, an MIT browser cube. Code solves. Jev decides whether the coach speaks. A removed test left Kociemba distance at 22 after forty move picks.

jev-rubiks

Ishan Goswami

@TheIshanGoswami

Posted Exa's Jev demo at demos.exa.ai/jev-web-context. The post says web results make yes/no answers more accurate. The page we loaded does not print the pairs.

Exa demo

Latent Node

@latent_node

Posted Decider 1 (sd-1) on meraGPT. The blog has no byline. Its table is accuracy 0.768 against Jev 1.13.0 at 0.727, KL 0.096 against 1.442, on teacher-average labels.

Decider 1

Idov Mamane

@idovmamane

idovmamane/dejevu, MIT. llama-3.3-70b on Groq finished the Flights check in 5.63 seconds. The Jev cell, 7.09 seconds, is jev-ultrafast's published number and was not rerun in that repo.

dejevu

Jose Mejias

@MejiasDev

mejiasd3v/pg-jev, MIT PostgreSQL extension. prompt_jev returns jsonb. The README prints no accuracy or latency table.

pg-jev

Pavel Hegler

@pavelhegler

backant-io/jevelry, MIT npm runtime. A JEVEL.md sets act, mark, and fall_back thresholds. The last live test in the README is three calls in 2.49 seconds on jev-1.13.0.

jevelry

Peter

@LordMarket22

Posted a 612-row banking-feed categorization. Jev 1.13 at 36.1% and $0.023 in 6 seconds. Gemini 3.7 Flash at 42.5%. No repository in the post.

Banking feed

Jinzhengxu

poker-table

GitHub account on Jinzhengxu/poker-table, GPL-3.0. The September 22 post that links it is @bigdicksinapig. Jev reads the opponent. Code picks the bet. Spot-bank median about one second. The post's live pill says 545 ms and $0.002 a hand.

Poker