DEMO / RECORDING
Overview & result
A write-up of driving a dual-arm robot with the typed decision AI model Jev 🦾 Of the three control layers, the decision layer (layer 2) is handed to Jev, while IK and physics calculations are kept in code. Responses take 500 ms and each trial costs 0.5 yen, so it is fast and very cheap.
Show the original post (Japanese)
型付き意思決定AIモデル「Jev」で双腕ロボを動かした結果まとめてみた🦾
3層制御のうち意思決定（2層）をJevに任せ、IKや物理計算はコード側に分離する構造を作りました。500msの応答と0.5円/試行で早くて激安。
How Jev fits in the loop
- Ingest real-time application state and relevant contextual parameters
- Format the decision problem as a bounded Choice or Noul schema
- Query Jev to receive a typed probability distribution over the options
- Execute downstream actions or route tasks according to the winning choice
How to reproduce
- Inspect the original showcase and source material at https://x.com/Raptor_zip/status/2101091398447505567
- Verify the bounded prompt and input candidate schema configured for Jev
- Benchmark decision latency and classification accuracy against baseline models
Why this build matters
Demonstrates a real-world, cost-effective implementation of Jev in a coding & developer tool scenario, replacing expensive generative calls with fast typed decisions.
Limitations
- Task accuracy is bounded by the precision of the defined candidate choices
- Third-party external dependencies and network latency may affect total workflow duration