Original Summary

I was fascinated by the possibilities that a System One Model like Jev can open, so I decided to recreate it from scratch within a fully embeddable runtime.<p>Performance is extremely good (less than 200 microseconds per decision), and memory is never allocated while scoring.<p>I created a self-running demo of Snake, Doom, and Autopilot that runs fully in a browser thanks to the WASM version.<p>I plan to add more experiments in the upcoming days, especially how a Blink-like decision system can fit into SQLite or Postgres.<p>Any feedback or participation to the project is more than welcome.<p>Repo: <a href="https:&#x2F;&#x2F;github.com&#x2F;sqliteai&#x2F;blink" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;sqliteai&#x2F;blink</a>

  • 情报分类：技术学习与提效
  • 分类依据：内容涉及技术、AI、软件工具或工程实践
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/9/22 21:16:04