CommunityJev Demos & Experiments
WORKLAUDE learn
A spoken-language learning experience where video scenes branch on TypeSafe Jev decisions instead of multiple-choice clicks.
- Format
- Playground
- Published by
- Community
- Last verified
- Oct 2026
- Platforms
- Browser
Highlights
- Show HN title: learn by speaking with scenes that branch on TypeSafe Jev.
- Access page asks for email and sends a link to open WORKLAUDE; no instant anonymous demo on that URL.
- Site branding routes learners through learn/plays once access is granted.
Watch out
Email gate on the public entry URL. Branching logic and Jev question design are not documented on the access page alone.
Questions about this entry
Short answers drawn from the linked project or page.
Not from the public entry URL. The entry copy says the access page sends a link that works for one hour and that there is no instant anonymous demo there; you pick a sequence after opening the link. It routes learners through the plays section once access is granted.
Not documented. The page lists sequences and scene counts, a job interview, a pharmacy visit, buying a train ticket, hotel check-in, an allergy order, five scenes each, but no scoring method, rubric, or per-scene feedback appears in the source or the entry copy.
The entry copy states plainly that the branching logic and Jev question design are not documented on the access page. You cannot audit or reproduce the routing without an account, so the model choice here is trust-based rather than reviewable.
Nothing published suggests it does. The listed sequences are English workplace and travel situations, and the page documents no language selector, level progression, or passing threshold. The access link also expires after an hour, which limits how far you can probe before re-requesting.
Six are listed: a job interview, at the pharmacy, bar night 2, buying a train ticket, checking in at a hotel, and ordering with an allergy. Each is five scenes, and the job-interview one covers introducing yourself, giving a strength with an example, and asking the interviewer a question.
You enter your email on the access page and it sends a link to open WORKLAUDE; the page says the link works for one hour. After opening it you pick a sequence and start speaking, in three documented steps.
Describing your symptoms to a pharmacist, answering her questions and understanding how to take the medicine, across five scenes. The train-ticket sequence similarly covers buying a return ticket, handling a platform change and finding your way.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Hacker News: Spoken-language learning with video scenes branching on TypeSafe Jev.
j_rcht1 pointShow HN: Worklaude – learn by speaking; video scenes branch on TypeSafe JEVRead the thread on Hacker NewsMore Jev resources like this
The official Laya playground: eight tabs that show choice, score, and noul decisions on ticket triage, phishing, guardrails, RAG filtering, moderation, routing, and multilingual text.
Jev Demos & ExperimentsPlayground#community#open-models#playground
Community
A ZeroGPU demo of Julia 1: define a state and any set of choice, score, and noul questions and see per-option probabilities rendered as bars and raw JSON.
Jev Demos & ExperimentsPlayground#community#open-models#playground
Community
A cinematic lunar expedition in the browser where Jev acts as flight director while telemetry, launch, and orbit scenes play out.
Jev Demos & ExperimentsPlayground#community#playground#games
Community
An independent browser playground that runs TypeSafe Jev on one question or several, with ready examples for routing, refunds, urgency, and the next agent action.
Jev Demos & ExperimentsPlayground#community#playground#tutorial
Community
The Cua computer-use platform documents a jev-use recipe where TypeSafe Jev picks bounded action IDs and Cua Driver executes clicks and fills in the browser.
Jev Demos & Experiments#community#browser#computer-use
Community
trycua/cuaRust
An agent skill that reproduces Jev-style single-step logits over indexed browser controls using local Qwen weights for offline browser use.
Jev Demos & Experiments#community#browser#open-models
Community
APUS-AI-Lab/fast-browser-usePython
From the Jev guides
Original write-ups on what this entry is for.
A game tick is a state plus a legal action list. How Clash Royale, Minecraft, and the earlier Mario, Pokémon, StarCraft, and drone loops ask Jev one step at a time.
Jev Demos & Experiments#gaming#agents#control
Read article
From the Jev community
Posts from builders shipping with Jev right now.