Back to benchmarks & research
jev-2048 project preview
Benchmarks & research

jev-2048

An instrumented 2048 web lab where every move is a Jev (TypeSafe AI System One) Choice, with no heuristic fallback | 用 Jev 决策模型驱动每一步的 2048 网页实验台,概率、置信度、延迟与成本全部摊开可见,且刻意不做启发式兜底

How it uses Jev

English readers: full English documentation → README.en.md A web lab that hands every move in 2048 to TypeSafe AI's Jev — a System One model that returns typed decisions with calibrated probabilities instead of generated text. Each turn is a single Choice over the four directions with no heuristic fallback , so every move stays attributable to Jev. Probability distribution, confidence, latency and token cost are sur…

Languages
TypeScript 85% · HTML 14% · Shell 1%
License
MIT
Latest release
2048 × Jev v1.0.0
Last activity
Sep 2026
Added
2026-09-22
Stars at snapshot
5
Status
Community listing
2048jevllm-evaluationsystem-onetyped-decisionstypesafe-ai

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README · the project website.

Listed in Jev Library

If this is your project, the badge below links back to this page. Paste it near the top of your README.

[![Listed in Jev Library](https://jevlibrary.dev/api/badge/arcj137442-jev-2048)](https://jevlibrary.dev/projects/arcj137442-jev-2048)

Something wrong on this page, or would you rather not be listed? Tell us and it will be changed.