Frontier LLMs

ICYMI: TypeSafe AI launches Jev for structured AI decisions

TypeSafe AI has emerged from two years of stealth with Jev, its first System One Model, now entering early access as developers are brought off the waitlist. The company positions the model as a fast decision layer for software, trading open-ended text generation for predefined, typed outputs that applications can consume directly. 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… pic.twitter.com/JSybNG2BKJ Jev accepts unstructured context, including text and structured program state, then returns probabilistic decisions with confidence scores.

The AI Multiverse Editorial Desk•Thursday, September 17, 2026•3 min read

Reported viaTestingCatalog AI News

Reader:

Executive Brief & 3-Point Takeaways

TypeSafe AI has emerged from two years of stealth with Jev, its first System One Model, now entering early access as developers are brought off the waitlist.

The company positions the model as a fast decision layer for software, trading open-ended text generation for predefined, typed outputs that applications can consume directly.

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… pic.twitter.com/JSybNG2BKJ Jev accepts unstructured context, including text and structured program state, then returns probabilistic decisions with confidence scores.

Impact:

Significant development in Frontier LLMs reported by TestingCatalog AI News.

Fact-checked against primary sourcesCategory: Frontier LLMs

ICYMI: TypeSafe AI launches Jev for structured AI decisions

Illustration: AI-generated

Key Findings & Takeaways

TypeSafe AI has emerged from two years of stealth with Jev, its first System One Model, now entering early access as developers are brought off the waitlist.
The company positions the model as a fast decision layer for software, trading open-ended text generation for predefined, typed outputs that applications can consume directly.
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… pic.twitter.com/JSybNG2BKJ Jev accepts unstructured context, including text and structured program state, then returns probabilistic decisions with confidence scores.

Why It Matters

Significant development in Frontier LLMs reported by TestingCatalog AI News.

Overview

Why It Matters

This development was reported by TestingCatalog AI News.

Key Details

Developers define the available choices and output structure in advance.

Rather than generating tokens sequentially, the model evaluates decisions in parallel.

TypeSafe says schema matching is guaranteed and type errors are mathematically impossible.

Its claim that Jev cannot hallucinate applies to the constrained output space, however, and does not mean every factual decision will be correct.

The model is priced at $0.042 per million input tokens, or $42 per billion, with no charge for output tokens.

--- *Original report published by [TestingCatalog AI News](https://www.testingcatalog.com/icymtypesafe-ai-launches-jev-for-structured-ai-decisions/).*