Jev (AI model)

Jev is a proprietary artificial intelligence model developed by TypeSafe AI, a San Francisco–based company founded in 2024.

Uses your system voice; voice and rate in settings.

Snapshot

≈ 5 min read

Names in other languages

No names in other languages are held for this entry yet.

Article bodies are English and are not machine-translated. A name in another language is not a translation of the article.

Jev is a proprietary artificial intelligence model developed by TypeSafe AI, a San Francisco–based company founded in 20241. It was released in limited early access on 15 September 2026, alongside the announcement of a US$40 million seed round led by DCVC. Jev is a discriminative model, that is, it is used for classification or regression, not generation.

It 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 software rather than read by a person.

Unlike classical discriminative models, Jev does not require data-specific training. Like generative pretrained transformer models, it can perform zero-shot learning of input for categories provided at inference time, based on contextual information provided at inference time.

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.

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. Jev is a discriminative model, that is, it is used for classification or regression, not generation.

It 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 software rather than read by a person.

Unlike classical discriminative models, Jev does not require data-specific training. Like generative pretrained transformer models, it can perform zero-shot learning of input for categories provided at inference time, based on contextual information provided at inference time.

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. A state is an entry. An entry is a string , JSON object , or array of string .

Examples: "My card was charged twice." {"message": "My card was charged twice.", "order_id": "A-104"} ["Hi", "My customer number is TS1337.", "My card was charged twice."] A question is a JSON object . Jev allows three types of questions, all multiple-choice.

Schematically: "new_noul_1": { "type": "noul", "instructions": " ", "criteria": { "true": , "false": } }, "new_choice_2": { "type": "choice", "instructions": "Which option fits the state?", "criteria": { "option_0": , ..., "option_n-1": } }, "new_score_1": { "type": "score", "instructions": "Where does the state fall on the scale?", "criteria": ["option_0": , ..., "option_n-1": ] } If the state is a JSON object , the question can also refer to attributes of the state . For example: {"food": "hotdog", "category": "sandwich"} "new_noul_1": { "type": "noul", "instructions": "Is `food` a `category`?", "criteria": { "true": "", "false": "" } } For a choice question, the answer's choice is just the most likely choice (i.e. the mode): \operatorname{mode}(p_0, \dots, p_{n-1}) := \operatorname{argmax}_i p_i For a noul or choice question, the answer's confidence measures how concentrated the probability distribution is around the mode: \mathrm{confidence} = \frac{p_{\max}-n^{-1}}{1-n^{-1}} where n is the total number of choices (i.e. n=2 for noul), and p_{\max} = \max \{p_0, \dots, p_{n-1}\} is the largest probability in the distribution.

For a score question, the answer's score is the probability-weighted average \sum_{i=0}^{n-1} ip_i , and confidence is defined as: \operatorname{confidence} = \max\!\left( 0,\, 1- \frac{\operatorname{MAD}(p_0, \dots, p_{n-1})} {\operatorname{MAD}(1/n, \dots, 1/n)} \right) where \operatorname{MAD}(p_0, \dots, p_{n-1}) := \frac 1n \sum_{i=0}^{n-1} |i - \operatorname{mode}(p_0, \dots, p_{n-1})| is the average absolute deviation around the mode.

Text derived from https://en.wikipedia.org/w/index.php?oldid=1378873287 under CC BY-SA 4.0; modifications have been made.

References

1 claim could not be tied to a specific sentence and is listed in the table below instead.

  1. ↩Wikipedia “Jev (AI model)” revision 1378873287 · retrieved 2026-10-21 date of foundation (×1) · confidence 0.95 revision URL