HN 提问：您如何管理本地长期研究项目和大型语言模型？
3 分•作者: ripplefringe•3 个月前
简而言之：您是否有使用大型语言模型（LLM）进行长期研究或非编码项目的模式或结构？
我受到了这篇 Hacker News 文章的启发，其中有人收集数据来解决他们的疲劳问题：https://news.ycombinator.com/item?id=48605117
我做过类似但规模较小的项目，就是收集芝加哥无坚果餐厅的信息。我收集了文章、评论、电子邮件、电话记录等各种信息。我发现使用 Copilot 作为我的界面非常方便，我反复将数据输入其中，并让它进行整理。
https://github.com/joshuabremer/chicago-allergy-eats
这似乎是一个常见的情况，人们会从事一项长期的研究或数据收集任务，并使用 LLM 来回答问题或帮助他们处理数据。有人有标准格式吗？或者有什么有效的例子可以分享吗？
查看原文
TLDR: Do you have a pattern or structure for doing long-lived research or non-coding projects using LLMs?<p>I was kind of inspired by this hacker news article where someone collected data to solve their fatigue problem: https://news.ycombinator.com/item?id=48605117<p>A similar but smaller I did was to collect nut-free restaurants to eat in Chicago. So I had articles, reviews, emails, phone calls, all sorts of stuff. I found it very easy to just use Copilot as my interface and I just data into it over and over and asked it to organize it.<p>https://github.com/joshuabremer/chicago-allergy-eats<p>This seems like a common thing where people would be working on a longer-term research or data collection task where you use the LLM to answer questions or help you accept the data. Does anyone have a standard format for this? Or an example that is working for you?