Original Summary

I was thinking about how Advent Of Code and how coding has changed. I think it could be fun to participate in a challenge oriented website where the solution had to be &#x27;programmed&#x27; using a prompt using a local small LLM. The server would then check the correctness of the solution and somehow verify that the solution was generated with the small LLM.<p>I think it could be a good way to also teach and explore prompting styles with a specific objective in mind.<p>Does anything like this exist or does it sound interesting for someone to build?<p>There are some hurdles to overcome:<p>- what LLM would everyone use that is small enough to run on a webgpu (for example)<p>- how would the server verify the code was generated by the LLM and not tampered with (if that&#x27;s even possible)

  • 情报分类：服务器与云资源
  • 分类依据：内容涉及服务器、云资源或网络线路
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/10/17 23:52:13