I hate AI and I know with absolute certainty it will bring far more horror into human existence than we have ever known before. But thanks for this tutorial 😀
I’m usually a late comer to new technology. I didn’t get a smart phone till 2012
I didn’t get ChatGPT until this month. I love it.
I’m mainly using it to track health data. And I find it especially helpful in analyzing my daily BM’s. I upload a picture and ask it to analyze and advise. A doctor can’t or won’t do this for you. They simply do not have time, and this is not something they are trained for.
From ChatGPT-
I learned that I wasn’t absorbing fat properly. Malabsorption. Oxbile and digestive enzymes fixed this.
Maybe. While part of my comment was tongue in cheek, the idea that AI doesn’t pose serious risks to humanity in ways that hydrogen and the printing press don’t is unrealistic.
Spent £20, saved £20,000 within one month. Will save £500,000 over the next 20 years. I am a law geek and have now become a non-taxpayer. Writing legal notices and trusts used to take two weeks. Now it takes one hour. ChatGPT like most tools can be used for good or evil.
Love this, super useful. However the parts in the grey boxes suggested for copying into new conversations don’t appear to be copyable? Is there a workaround? Thank you!
I use most of these except the framework tip. Most of the output I get is valuable but I know when I use other uncustomized models it is total waste of time. Thanks for the structured tips!
Great points! It’s so easy to forget that majority of Ai users don’t operate the way the we think they do. I’ll be using these steps to make sure we’re all on the same page. Thank you!
Really thoughtful guide, Kamil. Especially appreciated the clarity around onboarding.
One thing I’ve been noticing though: when you heavily rely on tone shifts or prompt rhythm, strong personalisation can act like a soft filter. It doesn’t override the prompt, but it does seem to nudge the tone or pacing. It happens especially early in a thread or when prompts are a bit open.
Do you adjust your settings based on context or type of work? Curious how you manage that balance between consistency and flexibility.
Hi Kamil. I appreciate this post a lot. I think people hate on AI because they assume most are using it to write and create, which leads to the death of original ideas.
When I've used AI I've always thought of it as a research and organizational companion. My Chat GPT answers to a name. He's a mentor, a voice, and a place to organize thoughts. Interestingly, our conversations more often illustrate what I don't want to do, what I don't want to write, and get me from in my head to on paper a little bit faster. And if I need him to be a sales executive, a financial advisor, or a simple researcher — he quickly points me in the right direction.
I remain very curious how other people are using AI. But I will be implementing some of your actions to see how they work. Thanks for writing.
I did everything and I am amazed by the results. I thought I was already a guru, but seeing the results on your recommendation, I am still a baby in the world of AI. Thank you!
I hate AI and I know with absolute certainty it will bring far more horror into human existence than we have ever known before. But thanks for this tutorial 😀
😂🤙
I’m usually a late comer to new technology. I didn’t get a smart phone till 2012
I didn’t get ChatGPT until this month. I love it.
I’m mainly using it to track health data. And I find it especially helpful in analyzing my daily BM’s. I upload a picture and ask it to analyze and advise. A doctor can’t or won’t do this for you. They simply do not have time, and this is not something they are trained for.
From ChatGPT-
I learned that I wasn’t absorbing fat properly. Malabsorption. Oxbile and digestive enzymes fixed this.
What is BM anyway?
I would assume bio markers. I wondered by what message Te is measuring them
Bowel Movement, sorry I was figured everyone knows what a BM is. My bad.
I upload a picture to chatbox. Have it log it analyze and advise.
No doctor could ever do this for you.
G, I thought it meant bowel movement.
Bowel Movement
From a daily picture, really? The world is going to 💩 faster than I thought.
So how in the world you got into Substack ? Hahahahaha
That’s crazy. What have you done to improve things.
I’ll have to go to chat GPT and get it to explain what you’re talking about.😂
Maybe. While part of my comment was tongue in cheek, the idea that AI doesn’t pose serious risks to humanity in ways that hydrogen and the printing press don’t is unrealistic.
Poor Jeff. You probably hate hydrogen too. Just HATE hydrogen. Because it leads to, you know,…. Everything.
Yes
Clearly... You've not gotten the main idea 💡
I think I have. It's why I have reservations. Surprising that others can view AI as an unalloyed good. Really surprising.
Great write up and I will try this out!
DANG. i get it but why humanity? why wish for more suffering
hmmmm….. doesn’t BM mean bowel movement?
I’m sure that’s what some said about the printing press or electricity or the internal combustion engine at the beginning…
Great.
I like how clearly you delivered this.
I like how chatgpt helped the author deliver that so clearly.
And no em dashes!
you’ll enjoy todays edition ;)
Spent £20, saved £20,000 within one month. Will save £500,000 over the next 20 years. I am a law geek and have now become a non-taxpayer. Writing legal notices and trusts used to take two weeks. Now it takes one hour. ChatGPT like most tools can be used for good or evil.
You will love today’s edition
OK you've got me, I have subscribed. You might like this I wrote with chatGPT.
Blew my tiny mind!
https://truthaddict.substack.com/p/the-quantum-field-is-conscious
The people complaining that "ChatGPT gives generic advice" are the same ones who never briefed it like a team member.
AI’s not your muse, sweetie, it’s your intern. And it needs training.
Honestly? This should be required reading for anyone paying $20/month and still using GPT like it’s Ask Jeeves.
Love this, super useful. However the parts in the grey boxes suggested for copying into new conversations don’t appear to be copyable? Is there a workaround? Thank you!
Hey, thank you for the feedback. I will work on this. In the meantime, if you open the article in the browser it should be Easier to copy it
I use most of these except the framework tip. Most of the output I get is valuable but I know when I use other uncustomized models it is total waste of time. Thanks for the structured tips!
Perfect post!
You forgot to mention the use of “projects,” “instructions,” and “grade” within and outside of the project environment.
In principle, using these, you’ll get the customized behavior without the need to instruct ChatGPT.
That said, your setup resembles mine, although the subject matters are completely different.
Great points! It’s so easy to forget that majority of Ai users don’t operate the way the we think they do. I’ll be using these steps to make sure we’re all on the same page. Thank you!
Thanks for sharing these info!
Have you tried customizing it?
Yes I do.
Really thoughtful guide, Kamil. Especially appreciated the clarity around onboarding.
One thing I’ve been noticing though: when you heavily rely on tone shifts or prompt rhythm, strong personalisation can act like a soft filter. It doesn’t override the prompt, but it does seem to nudge the tone or pacing. It happens especially early in a thread or when prompts are a bit open.
Do you adjust your settings based on context or type of work? Curious how you manage that balance between consistency and flexibility.
In EDGE cases, I ask it to ignore the personalization settings. It seems to work.
Yes, including "Ignore any personalisation settings" etc. in the prompt does help. Fully agree.
Hi Kamil. I appreciate this post a lot. I think people hate on AI because they assume most are using it to write and create, which leads to the death of original ideas.
When I've used AI I've always thought of it as a research and organizational companion. My Chat GPT answers to a name. He's a mentor, a voice, and a place to organize thoughts. Interestingly, our conversations more often illustrate what I don't want to do, what I don't want to write, and get me from in my head to on paper a little bit faster. And if I need him to be a sales executive, a financial advisor, or a simple researcher — he quickly points me in the right direction.
I remain very curious how other people are using AI. But I will be implementing some of your actions to see how they work. Thanks for writing.
This is a very useful tutorial. You have to give AI a bit of "you" to get amazing results.
Wow! These tips are excellent. I appreciate your post on the subject. Subscribed.
Thank you, please let me know if you need any help
I did everything and I am amazed by the results. I thought I was already a guru, but seeing the results on your recommendation, I am still a baby in the world of AI. Thank you!
Insightful article, thank you sharing!
This tutorial worked great on Pi.ai Thank You! 😘❤️
Nice to see they are still around