Ask HN: 大型语言模型 (LLM) 仅仅是昂贵的搜索和脚本工具吗? 真的就这么简单吗?

3作者: edwin27 个月前
所有大型语言模型(LLM)是否都可以被概括为一种(目前)非常昂贵的搜索,它允许你表达细致入微的查询并编写搜索结果的脚本?为什么或为什么不? 以代码为例。从某种意义上说,StackOverflow 就像是在为已经解决的问题寻找代码片段。自动补全在某种程度上也做了同样类型的搜索。 以生成文本为例。从某种意义上说,这相当于提出一个查询,然后将多个结果聚合到一个短语中。你可以想象机器人搜索 1000 个网站,然后取查询答案的平均值,最后输出结果。 每个 LLM 的用例都符合以下模式吗? 查询 —-> LLM 执行其工作 —-> 结果 —-> 结果脚本(可选)
查看原文
Can all of LLMs be summarized as a (currently) really expensive search that allows you to express nuanced queries and script the output of the search? Why or why not?<p>Take code. In a sense, StackOverflow is about finding a code snippet for an already solved problem. Auto complete does the same kind of search in a sense.<p>Take generative text. In a sense that’s the equivalent of making a query and then aggregating the many results into one phrase. You could imagine the bot searching 1,000 websites and then taking the average of the answers to the query and then outputting the result.<p>Does every LLM use case fit the following pattern?…<p>query —-&gt; LLM does its work —-&gt; result —&gt; script of result (optional)