瀏覽器使用 + Jev
Gregor Zunic 的動態 DOM 操作空間飛行搜尋示範。
A FIELD GUIDE TO JEV / VOL. 01
匯集 Jev 的真實專案、實用指南和來自全網的創意。
Gregor Zunic 的動態 DOM 操作空間飛行搜尋示範。
01 / A small decision engine. A whole new way to build.
65 項資源 / 資源集
重設篩選AI-assisted summaries and translations. Check original sources for context and performance claims.
為軟體而非對話設計的機器原生智能的論點。
發布文章:架構、RLCD 訓練、定價、Doom 與 Wikiracing 示範、常見問題。
貼上狀態,加入問題,並在瀏覽器中查看類型化答案。
TypeSafe 官方伺服器。Builder 示範位於「展示與分享」頻道。
公開 System One 工作流程的評估方法和各模型的結果。
公司首頁、等候名單及產品概覽。
3D chess where Jev plays both sides, or you jump in.
X client with Jev smart rules that filter the timeline by usefulness, type, and topic.
The Neuron's explainer on AI decisions without a chatbot.
Short practical intro with a Python ticket-triage example.
A practical guide explaining the use of TypeSafe’s System One model, providing technical insights for developers.
Independent walkthrough separating TypeSafe's published claims from public evidence.
Head-to-head test at validating local event listings, with cost and latency.
A guide explaining how to integrate Jev with Pydantic AI agents for type-safe operations.
Village NPCs that judge you each tick, deciding what to do and how they feel, instead of chatting.
@ai-sdk/typesafe-ai plus experimental_evaluate; use jev-latest as an evaluation model.
Small game that tests how Jev handles unknown input.
Japanese walkthrough of what Jev is and is not.
1,800-point thread debating whether typed decisions replace LLM calls for classification, routing, and scoring.
A tool for tracking decisions made by Jev, using Arize's instrumentation for detailed analysis.
Latent Space's launch-day roundup: over 100x faster and 200x cheaper than small frontier LLMs.
One sentence becomes six room settings. Jev chooses, the app renders.
A guide explaining Jev's approach to making typed decisions rather than processing text.
A report detailing all public Jev builds in the first week, including cost, time, and repository metadata for research use.