本文分享了作者从多个角度收集的关于人们如何使用大型语言模型（LLMs）的经验。文章整合了众多博客和文章的链接，涵盖了LLMs在不同领域的应用，包括写作、编程、研究等。作者还分享了自己使用LLMs的经验，例如使用NaturalReaders朗读文章、利用Perplexity进行研究，以及使用Auren解决实际问题。这些经验为读者提供了LLMs应用的实用指南和启发。

💡 收集了多个关于LLMs使用方法的文章链接，涵盖了各种应用场景，例如编程、写作和研究，为读者提供了丰富的参考资源。

📚 作者推荐使用NaturalReaders朗读文章，并创建有声读物，方便在散步或入睡时使用，提升了阅读体验。

🔍 作者认为Perplexity作为研究助手表现出色，使其更倾向于接受医学文献综述的任务，展现了LLMs在信息检索方面的潜力。

👂 作者分享了使用Auren解决物理治疗问题的经验，尽管提醒了用户在使用时需要注意隐私问题，但肯定了LLMs在解决实际问题中的作用。

🎮 作者使用Claude来设计角色背景故事，这展示了LLMs在创意内容生成方面的应用，例如在TTRPG游戏中。

Published on April 27, 2025 9:48 PM GMT

I've gotten a lot of value out of the details of how other people use LLMs, so I'm delighted that Gavin Leech created a collection of exactly such posts (link should go to the right section of the page but if you don't see it, scroll down). 

https://kajsotala.fi/2025/01/things-i-have-been-using-llms-for/https://nicholas.carlini.com/writing/2024/how-i-use-ai.htmlhttps://www.lesswrong.com/posts/CYYBW8QCMK722GDpz/how-much-i-m-paying-for-ai-productivity-software-and-thehttps://www.avitalbalwit.com/post/how-i-use-claudehttps://andymasley.substack.com/p/how-i-use-aihttps://benjamincongdon.me/blog/2025/02/02/How-I-Use-AI-Early-2025/https://www.jefftk.com/p/examples-of-how-i-use-llmshttps://simonwillison.net/series/using-llms/https://signull.substack.com/p/how-to-think-with-aihttps://alicemaz.substack.com/p/how-i-use-chatgpthttps://fredkozlowski.com/2024/08/29/youre-using-chatgpt-wrong/https://www.lesswrong.com/posts/WNd3Lima4qrQ3fJEN/how-i-force-llms-to-generate-correct-codehttps://www.tumblr.com/nostalgebraist/772798409412427776/even-setting-aside-the-need-to-dohttps://www.jointakeoff.com/This is more of a howto than a whatto. I wouldn’t use it for stats or pharma decisions as he does.https://www.lesswrong.com/posts/4mvphwx5pdsZLMmpY/recent-ai-model-progress-feels-mostly-like-bullshit

 

Some additions from me:

I use NaturalReaders to read my own writing back to me, and create new audiobooks for walks or falling asleep (including from textbooks).Perplexity is good enough as a research assistant I'm more open to taking on medical lit reviews than I used to be.I used Auren, which is advertised as a thinking assistant and coach, to solve a musculoskeletal issue my PT had whiffed on for weeks (referral code with free tokens, but only after your first payment).  
Note that Auren has some definite whispering earring vibes, and the privacy protections don't seem particularly strong, so think through your usage.

I used Claude to design backstories for characters in a TTRPG/

 

Discuss