最新

我为 Zig 语言开发了一个排序集合库的早期版本。排序集合是一种保持数据有序的数据结构。例如，Java 中的 `java.util.TreeMap` 和 C++ 中的 `std::map` 都是这类数据结构的代表。这些数据结构主要用于快速查找（点查询）和快速范围查询。<p>该库已在 GitHub 上发布：<a href="https:&#x2F;&#x2F;github.com&#x2F;CogitatorTech&#x2F;ordered" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;CogitatorTech&#x2F;ordered</a>

Hey HN, Enrico here. Some of you might remember Big-AGI from early chat days. The response here pushed me to quit my job and go all-in. Spent the last year rebuilding it properly (mostly hand-written) instead of shipping fast.<p>This is the tool I couldn&#x27;t find: the AI you use to decide what to build, and why, before going to Claude Code or Cursor.<p>Even though the hype is on AI that &#x27;does&#x27; things through heavy prompted experiences, I believe there&#x27;s a strong need for AI that helps you &quot;think&quot; broader. How? with multiple models in parallel so you can spot hallucinations and lies, and so you can explore the solution space faster. And also with human bandwidth optimization: UI&#x2F;UX is way underdeveloped for the &quot;wall of text&quot; phenomenon and hardly optimized for your I&#x2F;O bandwidth besides voice input. And designed to short the generation&#x2F;verification loop.<p>So Big-AGI 2 is now out, to be the fastest chat with a madly optimized UI, be local-first (app soon) because we don&#x27;t like to wait 150ms&#x2F;click. With Personas support because memories and data shall be with a relatable entity.<p>If the cost of mistakes is very high for your work - wrong arch decisions, debt-inducing bad tech choices, bling spots - do yourself a favor, and try it.<p>Anyone can Free&#x2F;unlimited at big-agi.com, or self-host from github.com&#x2F;enricoros&#x2F;big-agi (sync is Pro only, $11&#x2F;mo).<p>Worth building a thinking tool while everyone builds doing tools? Worth bootstrapping rather than VC-lubing? Genuinely curious.