After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x Show more
Kev
Apache-licensed, locally runnable Jev-style decision models (0.8B, 4B, 9B on Qwen3.5) with released weights, training code, a System One-compatible server, frozen eval suites, and a playground.
- Category
- Practices & Patterns
- Published by
- Community
- Author
- jaredpalmer
- Added
- 2026-09-22
Tagscommunitypythonopen-modelsbenchmarkscalibration
Highlights
- Weights for Kev-0.8B, Kev-4B, and Kev-9B are released on Hugging Face with training code and evaluation data.
- Its API matches TypeSafe's System One, so the official Python SDK can point at a local server; requests mix noul, choice, and score questions.
- Runs on CUDA, ROCm, and Apple Silicon; the 4B and 9B fit a 32 GB Mac in bf16, and a web playground permutes option order.
- On its frozen new-source test set the author reports Kev-9B at 0.852 versus 0.857 for hosted Jev, but Jev's training data is unknown.
- Fine-tuning gaps are documented: the first Kev-9B dropped deadline questions to 0.72 and KEV_DATE_FACTS=1 recovers 0.90.
Quickstart
bash
git clone https://github.com/jaredpalmer/kev.git && cd kev
uv sync --extra serve
KEV_DTYPE=bf16 uv run --extra serve python -m kev.serve --run jaredpalmer/kev-4b --port 8009Watch out
Apache-2.0, with the Qwen bases under the same license. Not a controlled architecture comparison because Jev's training data is unknown; needs Python 3.12+ and uv, and calibration and option order should be tested on your own data.
More like this
3.6kGitHub stars
An independent baseline that reads typed option probabilities straight from a frozen Qwen3.5-4B's logits in one forward pass, reproducing Jev's interface pattern with open models rather than Jev's undisclosed model or training.
Practices & Patterns#community#python#open-models
CommunitySemIf
296GitHub stars
An independent open reproduction of the System One model class: Qwen3.5-based 2B and 35B mixture-of-experts models that return typed Choice, Score, and Noul probabilities in one forward pass, with nothing distilled from Jev.
Practices & Patterns#community#python#open-models
Communitydecider
260GitHub stars
A ModernBERT-based open decision model that evaluates Choice, Score, and Noul schemas in one non-autoregressive pass; Verdict 2.0 reports 77.10% accuracy on 2,000 held-out enterprise decisions.
Practices & Patterns#community#python#open-models
CommunityopenJev-verdict-2.0
From the community
Posts from builders shipping with Jev right now.
The launch post
Trading bot, one decision per block
I built a trading bot with Jev! Jev decides if it should "buy" or "sell", given the price feed of an asset pair, and executes real trades. It uses Monad to place the orders on Kuru's on-chain order book in every 300ms block. Demo link → jev-trader.vercel.app
Classifying 1,500 real emails
this model is actually insane at email classification i tested it on 1500 of my own emails to see how well it works and I am blown away
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
Fast browser use with Stagehand
we built blazing fast computer/browser use with Jev + @Stagehanddev. this task cost $0.001 and executed at near instant speed (in a remote browser btw) the loop: observe the page, send a11y tree as state + actions as questions, Jev decides the next action, then Stagehand Show more
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
LLM-as-a-judge, sped up
Jev has spoken. It picked which model is AGI. 20–200x faster. 40–400x cheaper. This could make things like LLM-as-a-judge insanely fast and nearly free. (I tried a bunch of prompts and still didn’t burn through $0.10.)
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
Instant compaction with Jev
found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant