Skip to content
JevDirectory.org
CommunityTools & Integrations

Jev Playground (Formatho)

A browser builder for System One requests: define state plus Noul, Choice, and Score questions, preview mock distributions, and generate Python typesafe_sdk code.

Open formatho.com
Category
Tools & Integrations
Format
Playground
Published by
Community
Author
—
Added
2026-09-25
Last verified
2026-09-25
Tagscommunityplaygroundsdknoulchoice

Highlights

  • Documents the primitives: Noul as a 0 to 1 probability, Choice up to 255 options, and Score on 2 to 10 levels.
  • Warns that questions are parallel and independent, so a question that depends on another needs a second request.
  • Mock mode needs no key; live mode sends your own key straight from localStorage to the API.

Watch out

Live mode requires a TypeSafe key, and the page says SDK shapes should be re-verified against the docs.

Related terms

Glossary definitions related to this entry.

More like this

Crowdcheck
Test a social post on 10,000 simulated AI readers with their own jobs, tastes, and memories before the real internet sees it.
Tools & IntegrationsPlayground#community#playground#social-media
Community
Ship Pile
Describe the startup you are looking for and Jev ranks the pile, asking once per startup whether it is a fit.
Tools & IntegrationsPlayground#community#playground#search
Community
TypeSafe Playground (community)
21GitHub stars
A community playground with over a hundred use cases, games, and model challenges, with editable prompts and side-by-side comparisons.
Tools & IntegrationsPlayground#community#playground#nextjs
CommunityTypeSafeAI/typesafe-playgroundTypeScript
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Jev benchmarked on two public safety corpora

Gaurav Gosain
Gaurav Gosain
@_GauravGosain
·

1/ Benchmarked TypeSafe's Jev on two public safety corpora. It doesn't generate text, it returns calibrated probabilities you threshold in code. 96.5% on prompt injection, all 662 messages in deepset/prompt-injections. No tuning. 325ms p50.

Terminal dashboard showing 96.5% accuracy on prompt injection and 89.0% pairwise on vulnerable code, with a context ablation and calibration plot.
Diogo Almeida
Diogo Almeida
TypeSafe AI
@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

Watch on X
Reply
Read 1 reply

An open 151M-parameter decision engine

Hemant
Hemant
@heman10x
·

TypeSafe AI came out of stealth with Jev, and access is behind a waitlist. I built an open source version Verdict (Open-jev) you can run right now in a browser tab: And its a real post trained model..(link in comments) It is a post trained 151M parameters model. ModernBERT-base Show more

Image
Diogo Almeida
Diogo Almeida
TypeSafe AI
@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

Watch on X
Reply
Read 2 replies

Agent Handoff Gate: agents verify what they hand off

A local Telegram analyzer with Jev as the classifier

Dagmawi Babi
Dagmawi Babi
@DagmawiBabi
·

I vibe-coded this simple, open-source and local Telegram content analyzer using Jev as a classifier. Jev Classifier • jevclassifier.vercel.app Export your channel data as JSON and it will analyze each post's intent, quality, sentiment, and reaction tone and if it's a DM/Group Show more

Watch on X
Diogo Almeida
Diogo Almeida
TypeSafe AI
@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

Watch on X
Reply
Read 2 replies

A Krunker-inspired FPS, decided by Jev

Neel Patel
Neel Patel
@Neel490
·

Maybe I’m just washed, but Jev is beating me at my own game. Built a Krunker-inspired FPS where you 1v1 Jev. Try it out yourself: jev-arcade.vercel.app/duel

Watch on X
Diogo Almeida
Diogo Almeida
TypeSafe AI
@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

Watch on X
Reply
Read more on X

Pixel art out of 256 multiple-choice questions

Aryan Singh
Aryan Singh
@just_aryansingh
·

I turned @typesafeai Jev model into a pixel art model. 256 multiple choice questions, one per pixel, plus refinement passes. These were the best results out of the bunch I tested. Code: github.com/Wizhill05/type…

Image
Image
Image
Image
Diogo Almeida
Diogo Almeida
TypeSafe AI
@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

Watch on X
Reply
Read 1 reply