I made a DuckDB extension where you can use @typesafeai 's Jev to do quick classification of rows in any csv/parquet file or duckdb table about 10sec for 1k rows ~ better than using an LLM, way more ergonomic than a classifier game-changing for data analysis!
Yes / No — Free Jev Demo
A free no-signup demo that turns any question into Yes, No, or Maybe by calling jev-latest through TypeSafe's System One API, with live web search for questions that depend on current facts.
- Category
- Cookbooks & Demos
- Published by
- Community
- Author
- —
- Added
- 2026-09-22
Highlights
- Jev's probability below 45% reads No, above 55% Yes, and the 45-55% band yields Maybe no, Maybe yes, or Maybe.
- Questions needing fresh facts trigger a live Google search and a second Jev pass, and the page says when search was used.
- Fair-use limits are 100 questions per hour and 1,000 per day, with no account, API key, or stored questions.
- The demo calls jev-latest through TypeSafe's System One API, per the FAQ.
- Questions can be up to 1,000 characters, and answers are never random by design.
Watch out
A third-party demo from coderai.dev rather than an official TypeSafe page, and it returns a triaged answer without explanation.
More like this
From the community
Posts from builders shipping with Jev right now.
Classifying rows in DuckDB
A playable 16-judgment demo
typesafe's jev is fun! live demo you can play with: typesafe-demo.val.run
AI multiple choice, not essay writing
WTF is Jev by @typesafeai? Here’s the tl;dr ELI5: Think AI multiple choice, not AI essay writing. It doesn’t chat. It makes decisions your software can act on: “Spam or not?” “Which tool should this agent use?” “Does this need a human?” The exciting part: roughly 200x faster Show more
Screening agent actions with Jev
Tested TypeSafe’s Jev (no-text, probability-only model) as an AI agent safety monitor. Checking each action first worked well caught most attacks with almost no false blocks, and much faster than Gemini.
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
Cua's small System One models
1/ Introducing CUA-S1: a family of System One Models, small, specialized, and built for computer use. Today we're open-sourcing CUA-S1-FORMS, the first in the family: github.com/trycua/cua
A 706K-parameter form filler
cua open sourced a 706k param model that fills a whole form in one 50ms pass the llm agent doing the same form took 23 turns and 39.6 seconds the specialists are going to eat the generalists from the bottom
1/ Introducing CUA-S1: a family of System One Models, small, specialized, and built for computer use. Today we're open-sourcing CUA-S1-FORMS, the first in the family: github.com/trycua/cua
