Ask HN: LLM 算得上合格的 Lisp 吗？
3 分•作者: tdfirth•8 个月前
我这么说只是开个玩笑，但这确实是个有趣的小想法。<p>很容易证明，大型语言模型（LLM）这个“程序”是同像的，因为代码和数据都只是纯文本。<p>LLM 还提供了丰富的元编程功能（编写提示的提示）。<p>它们甚至可以说提供了类似 Common Lisp 条件系统的特性。<p>当然，它们不操作符号表达式，所以硬要说它们是 Lisp（或任何其他编程语言）就有点牵强了，但它们似乎确实共享了许多相同的属性。
查看原文
I say this in jest, but it's a fun little idea.<p>It's easy to make the case that an LLM 'program' is homoiconic, as the code and the data are all just plain text.<p>LLMs also offer rich metaprogramming (prompts that write prompts).<p>They even arguably offer features like CL's condition system.<p>Of course, they don't operate on symbolic expressions, so it's a stretch to actually call them a lisp (or any other programming language), but they seem to share a lot of the same properties.