Jev (AI model)

Jev
Developer	TypeSafe AI
Release	September 15, 2026 (2026-09-15)
Stable release	jev-1.13.0
Type	Artificial intelligence model
License	Proprietary
Website	typesafe.ai

Jev is a proprietary artificial intelligence model developed by TypeSafe AI, a San Francisco–based company founded in 2024. It was released in limited early access on 15 September 2026, alongside the announcement of a US$40 million seed round led by DCVC.

Unlike a large language model (LLM), Jev does not generate natural-language text. It instead returns typed values together with probability estimates and confidence scores. Its output is intended to be consumed directly by other software rather than read by a person.

TypeSafe describes Jev as the first of a class of models it calls "System One models", a name the company says comes from fast, intuitive System 1 thinking as popularized by Daniel Kahneman.

Background

TypeSafe AI was founded in 2024 by Diogo Almeida, Erik Gafni and Sasha Sheng. Almeida, the company's chief executive, spent approximately four years at OpenAI working on reinforcement learning from human feedback (RLHF), InstructGPT, ChatGPT and GPT-4 before leaving in 2024.

The company positions Jev as a reliable model for automation and software, and as a response to overconfidence in existing models. Forbes: "We've been optimizing for humans and we're super human at pleasing humans." He has separately described his disappointment with conversational models as the origin of the project, telling TechCrunch that the technology amounted to "lightning in a bottle" that was nonetheless not useful.

Before the announcement, Jev was being developed in stealth for roughly two years. Forbes reported that the round valued TypeSafe at US$200 million.

Design & architecture

A Jev request consists of a block of state (a string, JSON object or array of text) together with one or more typed questions. The model evaluates every question against the state in a single parallel pass and returns structured answers rather than plain text.

Jev allows three question types (also called primitives):

Primitive	Purpose	Returns
Choice	Select one option from a defined set	Selected option, per-option probabilities, confidence
Score	Rate the state against ordered levels	Score, per-level probabilities, confidence
Noul	Evaluate a yes/no statement	Probability between 0 and 1

Because the answers are defined in advance, the model cannot return a value outside the supplied schema. TypeSafe presents this as eliminating hallucination and type errors.

However, TypeSafe has not published Jev's exact architecture, weights, or a technical paper. The company describes the model as transformer-based and trained exclusively on synthetic data. The method of training is Reinforcement Learning for Calibrated Decisions (RLCD), where probabilities are optimized against outcomes rather than against human rater preference. Outside observers have suggested the model may be built on an open-weight LLM.

Performance claims

TypeSafe reports end-to-end response times of 70 to 500 milliseconds. The company claims that Jev is 40 to 200 times faster and 40 to 400 times cheaper than frontier LLMs on comparable tasks, with peak figures of 193.6 times faster and 444.6 times cheaper on its own workflows.

TypeSafe states in its own technical notes that the workflows were created by members of its model-capabilities team, acknowledges possible bias, and describes the reported gains as likely to sit at the high end of real-world results.

Name

The model is named after 19th-century English economist William Stanley Jevons, whose Jevons paradox describes how more efficient use of a resource can increase consumption. Almeida has said the name reflects an expectation that cheaper machine intelligence will lead to far wider deployment.

External links

• Official website
• Developer documentation for Jev