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
Jev (AI model)
Wikipedia's article on Jev: TypeSafe AI, the September 15, 2026 early-access release of jev-1.13.0, the Choice, Score, and Noul primitives, RLCD training, and the unpublished weights and technical paper.
- Category
- Sites & Guides
- Published by
- Community
- Author
- —
- Added
- 2026-09-22
Tagscommunityarticlemodelsarchitecture
Highlights
- Released September 15, 2026 in limited early access as jev-1.13.0, alongside a $40 million seed round led by DCVC.
- Founded in 2024 by Diogo Almeida, Erik Gafni, and Sasha Sheng; Almeida spent about four years at OpenAI on RLHF, InstructGPT, ChatGPT, and GPT-4.
- Lists Choice, Score, and Noul primitives and says answers cannot fall outside the supplied schema; TypeSafe presents this as eliminating type errors.
- States TypeSafe has not published Jev's exact architecture, weights, or a technical paper; outside observers suggest an open-weight LLM base.
- Names RLCD (Reinforcement Learning for Calibrated Decisions), trained on synthetic data with probabilities optimized against outcomes, not human preference.
Watch out
A community-edited encyclopedia entry built from vendor posts and press coverage; its speed and cost figures are TypeSafe's self-tested claims, which the article notes likely sit at the high end.
More like this
The Register's launch report on TypeSafe AI's Jev: the $40 million raise, typed probabilistic decisions, the Doom demo, the 70-500 ms latency and $0.042/MTok pricing claims, and the structured-output caveat.
Sites & GuidesArticle#community#article#press
Community
Tom's Hardware's launch report on Jev, covering how the API takes program state and typed statements and returns yes/no answers, choices, or probability distributions with confidence values.
Sites & GuidesArticle#community#article#api
Community
Latent Space's AINews roundup of launch day: the Jev thread atop Hacker News, the RLCD decision-model framing, and community readings that compare it to DSPy-style typed signatures for routing and scoring.
Sites & GuidesArticle#community#article#models
Community
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