Jev × 2048
Web lab where Jev plays 2048, showing each move's probability distribution, confidence, latency and token cost.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
Jev x 2048 is a hosted web lab in which Jev acts as the decision engine for the game 2048. For every move it displays the probability distribution over directions, the confidence, latency and token cost of the call.
The stated purpose is to let users watch how context design shapes a decision model's behaviour: how the board state is described and what evidence is included changes the move Jev picks. No source repository or README was available, so implementation details are not documented.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Which direction should the board be moved?(inferred) | up · down · left · right |
How it works
- Encode the 2048 board as state
- Jev chooses a move with probabilities
- Game applies the move and shows latency and cost
- User experiments with context design
Strengths
- Makes probability, confidence and cost visible per decision
- Useful teaching tool for context design
Caveats
- Hosted demo only; code not available
- 2048 is a game-tree problem that text decision models are not designed for
At a glance
- Type
- Demo
- Status
- prototype
- Runtime
- browser
Use cases and integrations
How curated lists describe it
A web lab where Jev is the 2048 decision engine, showing each move's probability distribution, confidence, latency, and token cost so you can watch how context design shapes the decision model.
AnotiaWang/awesome-decision-models
Frequently asked questions
What does Jev decide?
Which direction to move on each 2048 turn.
What is the point of the lab?
To show how the way you describe the board changes Jev's decisions.
Can I see the code?
No repository was linked in the list.
Related projects
Public Jev lab centred on a chess match broadcast where Jev picks from legal moves, plus smaller judgment booths and a Fast Flag catalogue.
ProjectprototypeJavaScript, Python25-second Japanese IT-buzzword game that shows Jev's speed and cost: every typed term is classified live, with no LLM-generated text.
ProjectprototypePython, JavaScriptVisual workbench (in Portuguese) for wiring Jev decision funnels as node graphs and watching them play a game in real time.
ProjectprototypePythonTic-tac-toe teaching project comparing Jev Choice, Score and Noul designs across three levels of state detail.
ProjectresearchJavaScriptJapanese quiz demo where Jev guesses which of AWS, Azure or Google Cloud a debranded service name belongs to, showing its probabilities.
DemoprototypeTypeScriptStreamlit Tetris demo where Jev picks one collision-checked placement ID and Python verifies cells before locking.
AppprototypePython