TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

A Lisp REPL Inside ChatGPT

10 点作者 madmax96超过 2 年前

3 条评论

hospadar超过 2 年前
I often have read &quot;I wonder if it _really_ understands or is just regurgitating ${something}&quot; about AIs like this and I wonder what the difference really is? Ability to explain why it&#x27;s one way and not the other? Extremely low frequency of errors? If it doesn&#x27;t really understand lisp, maybe we&#x27;d expect to see a fairly high rate of incorrect interpretations?<p>Presumably most _actual_ compilers don&#x27;t produce the correct solution 100% of the time (i.e. they have bugs), but I think it&#x27;s reasonable to say that the compiler _understands_ ${programming language}. Maybe the difference between &quot;understanding&quot; and &quot;just memorizing answers&quot; is more subtle than often portrayed?
评论 #33870468 未加载
narush超过 2 年前
Cool post -- wondering, does the final example of defining the y combinator and using it really show much? `(factorial 5)` probably would run without defining the y combinator first -- would be interested to see how it handled some novel function that isn&#x27;t probably directly memorized.
singularity2001超过 2 年前
(setf factorial (FUNCALL Y …<p>(factorial 5) 120<p>The author should at least have tested a counter-example<p>(setf factorial (red hot chilly nonsense))<p>I expect the &#x27;evaluation&#x27;<p>(factorial 5) 120<p>to be &#x27;correct&#x27; regardless of the function definition!