A probability-aware evaluation harness that compares TypeSafe Jev with GLiNER2.5 on zero-shot single-label text classification, measuring calibration, coverage at a fixed error budget, latency, and token cost.
git clone https://github.com/AbdelStark/jev-benchmarks.git
cd jev-benchmarks
uv sync --extra benchmark --dev
uv run jev-bench prepare --config configs/pilot-v1.yaml
export TYPESAFE_API_KEY=YOUR_API_KEY
uv run jev-bench run --config configs/pilot-v1.yaml --backend jevWatch out
Apache-2.0-licensed and requires Python 3.11-3.13, uv, and a TYPESAFE_API_KEY for the Jev backend; GLiNER downloads a pinned checkpoint on first use, and the reported numbers come from a 300-example pilot, not a leaderboard.
Posts from builders shipping with Jev right now.
The case against Jev-scored compaction
This is a terrible compaction strategy that fundamentally doesn't understand how compaction and context management work. Seems like a lot of people are confused so let's break this down. 1. Compaction isn't a filter The role of compaction is to clean up history to keep the Show more
found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant
Classifying rows in DuckDB
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!
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
