Show HN: GlyphLang – 一种 AI 优先的编程语言
1 分•作者: goose0004•6 个月前
在进行一个概念验证项目时，我一直遇到 Claude 的 token 限制，通常在 5 小时会话的 30-60 分钟内达到。来自代码库的累积上下文迅速消耗了 token。因此，我构建了一种语言，旨在由 AI 生成，而不是由人类编写。
GlyphLang
GlyphLang 用符号替换冗长的关键字，从而更有效地进行 token 化：
```
# Python
@app.route('/users/<id>')
def get_user(id):
user = db.query("SELECT * FROM users WHERE id = ?", id)
return jsonify(user)
# GlyphLang
@ GET /users/:id {
$ user = db.query("SELECT * FROM users WHERE id = ?", id)
> user
}
@ = route, $ = variable, > = return. 初始基准测试显示，与 Python 相比，token 减少了约 45%，与 Java 相比，token 减少了约 63%。
```
实际上，这意味着更多的逻辑可以融入上下文，并且会话在达到限制之前可以持续更长时间。AI 可以在整个过程中保持对代码库更广泛的了解。
在有人问之前：不，这并不是一个多此一举的 APL。APL、Perl 和 Forth 都是符号密集的语言，但它们针对数学符号、人类简洁性或机器效率进行了优化。GlyphLang 专门针对现代 LLM 的 token 化方式进行了优化。它旨在由 AI 生成并由人类审查，而不是相反。也就是说，如果需要，它仍然具有足够的可读性，可以编写或调整。
它仍在开发中，但它是一种可用的语言，具有字节码编译器、JIT、LSP、VS Code 扩展、PostgreSQL、WebSockets、async/await、泛型。
文档：[https://glyphlang.dev/docs](https://glyphlang.dev/docs)
GitHub：[https://github.com/GlyphLang/GlyphLang](https://github.com/GlyphLang/GlyphLang)
查看原文
While working on a proof of concept project, I kept hitting Claude's token limit 30-60 minutes into their 5-hour sessions. The accumulating context from the codebase was eating through tokens fast. So I built a language designed to be generated by AI rather than written by humans.<p>GlyphLang<p>GlyphLang replaces verbose keywords with symbols that tokenize more efficiently:<p><pre><code> # Python
@app.route('/users/<id>')
def get_user(id):
user = db.query("SELECT * FROM users WHERE id = ?", id)
return jsonify(user)
# GlyphLang
@ GET /users/:id {
$ user = db.query("SELECT * FROM users WHERE id = ?", id)
> user
}
@ = route, $ = variable, > = return. Initial benchmarks show ~45% fewer tokens than Python, ~63% fewer than Java.
</code></pre>
In practice, that means more logic fits in context, and sessions stretch longer before hitting limits. The AI maintains a broader view of your codebase throughout.<p>Before anyone asks: no, this isn't APL with extra steps. APL, Perl, and Forth are symbol-heavy but optimized for mathematical notation, human terseness, or machine efficiency. GlyphLang is specifically optimized for how modern LLMs tokenize. It's designed to be generated by AI and reviewed by humans, not the other way around. That said, it's still readable enough to be written or tweaked if the occasion requires.<p>It's still a work in progress, but it's a usable language with a bytecode compiler, JIT, LSP, VS Code extension, PostgreSQL, WebSockets, async/await, generics.<p>Docs: <a href="https://glyphlang.dev/docs" rel="nofollow">https://glyphlang.dev/docs</a><p>GitHub: <a href="https://github.com/GlyphLang/GlyphLang" rel="nofollow">https://github.com/GlyphLang/GlyphLang</a>