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.html
https://benjamincongdon.me/blog/2025/02/02/How-I-Use-AI-Early-2025/
https://fredkozlowski.com/2024/08/29/youre-using-chatgpt-wrong/
https://www.lesswrong.com/posts/WNd3Lima4qrQ3fJEN/how-i-force-llms-to-generate-correct-code
https://www.tumblr.com/nostalgebraist/772798409412427776/even-setting-aside-the-need-to-do
This is more of a howto than a whatto. I wouldn’t use it for stats or pharma decisions as he does.
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 physical therapist 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/
@Alex Lawsen has written about this too:
https://lawsen.substack.com/p/another-conversation-about-other
https://lawsen.substack.com/p/notebooklm-podcasts-but-good
https://lawsen.substack.com/p/getting-the-most-from-deep-research
https://lawsen.substack.com/p/my-current-writing-workflow
https://lawsen.substack.com/p/my-current-claude-projects
Interested what makes you say that, since I’ve been trying it out for about a week and haven’t gotten that vibe. I’ve found it useful for getting more awareness into my patterns, but the way I interact with it feels very me-driven. I choose what topics to bring up with it, when to continue or drop a conversation, etc. So far at least it hasn’t felt like it would have made any decisions for me, though conversations with it have shaped some small decisions (e.g. after I have a conversation with it about how doing X makes me feel worse, I had a slightly easier time remembering not to do X later).
I was pointing at the capacity to form a dependence on it, especially without realizing the extent, rather than decision making per-se.
Got it. The term implies something much more specific to me.
See also:
https://borretti.me/article/how-i-use-claude
I was planning on putting a whole list here but alas I am drawing a blank.
There’s a lot of dispersed wisdom in @Zvi’s stack too but I can’t remember any sufficiently discriminatory key words to find them.
A great collection of posts there. Plenty of useful stuff.
This prompted me to write down and keep track of my own usage:
https://vale.rocks/posts/ai-usage