Breaking: Browser Use + Jev = Ultrafast ⚡ Findings flights took 7s and cost only $0.0039 🤯 > new action space every step > DOM state space > small LLM fallback to type (this video is at 1x speed btw) Built a tiny open source browser agent. try it below ↓
Agentic RL 零基础教程
A 25-chapter Chinese tutorial that goes from reinforcement-learning basics to GRPO training with a runnable minimal-verl example, and closes with a chapter on when judgment tasks should be externalized to Jev instead of trained.
- Category
- Sites & Guides
- Published by
- Community
- Author
- cookiespiggy
- Added
- 2026-09-22
Tagscommunitypythontutorialagents
Highlights
- Chapter 25 argues single-step discriminative tasks can be delegated to a judgment model, while multi-step credit assignment and orchestration still need RL.
- It notes reward functions run millions of times with millisecond budgets, while Jev answers in 70-500 ms, so external judgment does not fit the training loop.
- minimal-verl is a runnable path from synthetic data to SFT, GRPO, and evaluation using Qwen2.5-0.5B and TRL's GRPOTrainer, with MPS support on Macs.
- Twenty-four other chapters cover PPO, DPO, RLVR, reward shaping, framework choice, data prep, agent training, evaluation, and distributed rollouts.
Quickstart
bash
cd minimal-verl
uv sync
uv run python scripts/00_check_env.pyWatch out
MIT-licensed for the tutorial. It is Chinese-language, and the minimal example trains a small Qwen model rather than producing a production model.
More like this
787GitHub stars
An evidence-backed community collection of Jev use cases, patterns, prompts, and starter code, with quick facts sourced to TypeSafe docs and runnable Python and TypeScript quickstart examples.
Sites & Guides#community#awesome-list#tutorial
Communityawesome-jev-by-typesafe
10GitHub stars
A selective awesome list of Jev projects, integrations, and resources: 241 entries each checked to actually call Jev, admitted at a 10-star bar, and paired with hands-on reviews at mrjev.com.
Sites & Guides#community#awesome-list#python
Communityawesome-jev
A Python walkthrough of typesafe-sdk: sync and async clients, grouping answers into choices, scores, and nouls, and routing uncertain cases to review, with arithmetic kept in Python.
Sites & GuidesArticle#community#tutorial#python
Community
From the community
Posts from builders shipping with Jev right now.
Browser Use Ultrafast, powered by Jev
A really smart switch statement
hype-free explanation of jev: jev does not replace gpt / claude jev is just a *really* smart switch statement like if 2016 ml classifiers got 2026 levels of intelligence it's a new* type of tool that will make a lot of workloads insanely fast, cheap, and accurate * = and by Show more
@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
When a designer gets Jev
when a designer gets access to Jev
Full Jev video tutorial
Full Jev Tutorial What it is, how you can build with it and what new applications it can unlock → 0:00 Intro → 0:34 Jev explained → 4:06 API setup → 5:59 Demo 1: Voice-controlled browser → 11:33 Demo 2: AI memory → 17:27 Demo 3: YouTube predictor
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!
