This was very long but I read the whole essay. I kept finding myself thinking, "yep" both as an assisted writer myself, and as a writing instructor. I appreciate how you articulated your process. You gave me a lot to think about and some things I want to try.
I find that using AI as an editor and repository for knowledge is empowering to the average citizen. Used incorrectly, it leads to incomplete thoughts and stale production. But used correctly it broadens our horizons and builds on the ability for normal people to write better without an editorial or research team.
I thoroughly enjoyed the article, and use AI to check my spelling and grammar when I am writing. Grammarly in particular, and when I need to flesh out an idea, or write in my native Scot's dialogue, I will use ChatGPT, mostly to check the sentence construction and other grammar related things. Sometimes it help me form what I am trying to say too.
Now a little bit about my background. I missed a lot of school due to illness when I was a child. From age 5 to 12, I was in and out of hospital, which meant I missed a lot of the formative years of Math and English. It's only now, at 42, that I can really say my math is where it should be, but for some stuf, without a calculator, I'd still be lost.
When it comes to English, I've had to fight through years of being told, your writing is terrible, you don't know how to use punctuation, that's not a paragraph... you get the picture.
What AI has done for me is open a door. A door that I can walk through and build my confidence, it can coach me on writing and grammar, punctuation etc, and explain why x is better to use than y. Could I have paid for a tutor, possibly, but when I work as much as I do, finding time is nigh on impossible, but again, AI has given me a way to tell my own story.
Again, as many of you will see, this post is done without AI assistance, and you can see how poor my grammar is, but, quite honestly, I don't really care. Because like you , Michael, I have found that I like to write fiction, I absolutely love world building and letting miy imagination run wild.
Anyway, thank you for writing, and showing the positives of your process
I loved this article! What interested me is that I can often tell on Substack when an author has used AI because of the usual "tells" (which I don't mind as long as their ideas are interesting), but with this, I honestly would never have known. You have a very clear and distinct voice that I found engaging and valuable to read, and clearly you have learned how to prompt.
Thank you for pointing out the ways in which AI assistance can boost not only one's critical thinking, research skills, etc., but can also increase a writer's confidence. While I am coming to this topic from the creative writing side, many of the same points you made are equally applicable there. Brainstorming and editing with AI have made me think in new ways, and consider new perspectives, that I wouldn't have encountered without it.
As a fellow neurodivergent, albeit one to whom writing has always come easily, I am fascinated by hearing from so many neurodivergent people that AI has finally enabled them to make their thoughts cohere. I wonder if this is less an issue of our thoughts cohering, and more an inssue of our thoughts not making sense to neurotypicals? One example I saw recently was an ADHD writer who would get frustrated because people seemed unable to follow the points she was making. She could clearly see the connections between them; neurotypical readers could not. Was this a failure of her writing, or merely a cognitive difference making neurotypicals unable to follow?
Thanks for the kind words. I think there are a great many neurotypical misconceptions. For example, I can’t take notes because if I do I can no longer follow what I am supposed to take notes about. I find it fascinating that the conversation about AI has surfaced so many supposedly critical skills that many neurodivergent people find to be a hindrance rather than helpful.
They're not mutually exclusive! Yes, AI can be used to outsource your thinking, but there are ways to use it that improve your thinking. I'm using it to analyze my writing, improve my French, and double check my analysis of my library's circulation to identify trends I didn't catch. You don't have it surrender your critical thought when using AI, and that's what I try to impart to my students.
Sorry, your "outsourced" thinking and analysis is based on research, writing, and decades of work from people like me stolen by tech companies, digested in data centers that consume environmental resources, through the efforts of exploited workers. That will be a hard no.
In terms of trends, perhaps check out this report:
Unlawful by Design: Exposing the Human Rights Costs of Generative AI
I’m aware of these things, and I have thought a lot about all the points you mentioned. But I’m a school librarian, and my students are going to use AI regardless. I’d rather model for them the most ethical ways it can be used rather than leaving them to muddle through it unguided (which will inevitably mean they’ll use it to cheat). I don’t have the choice not to grapple with it in my work.
I also believe that, since it isn’t going anywhere, I should try to influence how it develops. Which, again, means showing people how to use it for things other than putting in some ill-considered, poorly written prompt and accepting the first output as gospel. As I said before, there are ways to use it that can augment and improve your critical thinking.
I have very similar experiences. Sadly, the moral case for AI assistance is not well understood or widely held. I have found my writing has improved significantly, whether AI-assisted or not. I think it could help many students who struggle with their writing to improve if used as you describe your workflow.
AI is starting to become mainstream. There was a bit of a backlash against AI assisted anything. But I am starting to see a lot of AI generated content in traditional media that nobody seems to be upset about. I think the relationship with that medium will normalize.
I write for law reviews. They are adding AI disclosure policies that range from acknowledgement of AI usage to outright bans. It's strange to me because I know that many faculty members use student researchers to draft substantial research memos, and colleagues make substantial comments. In legal practice, the question is who takes responsibility, not who drafts. So, I suspect there is some fear and protectionism at work. I recently saw someone on-line who found a hallucination in a paper and wanted to have the author backballed.
Thankyou Michael for sharing your method in such a detailed way. These honest accountings of human-AI collaborations are tremendously helpful. I have found the new models capabilities helpful in settling some challenges you have identified. For example Claude Fable can quickly set voice calibration skills and style guides (eg I now apply skills rather than uploading samples). Increased capabilities in terms of persistence between chats also helps (eg working in projects increasingly common across LLMs by various names). I have also found your suggested multi-model workflows valuable, particularly for verification, and am now developing various apps with Claude Fable for source verification (early stages). Thank you for sharing.
Yes, thanks for the comment. I have recently made a few changes to my workflow. One thing that I did is that I finally decided to work with Cowork rather than just Chat in Claude. I might write an update some time in the future.
Thanks Michael. I’d be interested in reading your experience with Cowork as i’m just about to shift to a sandboxed environment and experiment with Cowork and connectors.
I enjoyed reading this Michael and as a neurodiverse person too with a good part of my life in academia transitioning from idea to text would take me weeks of refining - whilst I watched peers conduct the transition in days, or hours.
I've noticed a similar process developing in my writing too. Exposure to new grammatical forms and combination of ideas. At the heart of it I decide ultimately, how the language is constructed, however AI help fold out some of my ideas!
Thanks for the comment. I am still using pretty much exactly the same workflow although I have to admit that the latest versions of Gemini have a really good writing style for my type of content. It has become a viable option to stay completely within the Google ecosystem.
Great piece. Thanks for sharing your process and that’s a lot of back and forth between tools!
It sounds like your workflow is working but I’m wondering if you’ve explored trying to use Gemini ‘gems’ - inputting the writing guardrails you have to instruct the model how it should operate along with incorporating your research within a notebook from Notebook LM may allow for a one stop shop. Just some food for thought.
This is a powerful reflection on AI as an amplifier, not a replacement. Your process shows that judgment, creativity, and human discernment remain central, AI simply expands what you can achieve with them.
I talk about the latest AI trends and insights. If you’re interested in how AI acts as an amplifier for human judgment, creativity, and decision-making, check out my Substack. I’m sure you’ll find it very relevant and relatable.
I am amazed and thankful for your post. I have been using a similar process. I had also written a lot. Two books, over 90 articles. My writing was reasonably decent but I know writers. My mom is a writer. I was not a writer. AI assisted writing has liberated me, almost identical to the way it’s done it for you. I can go from idea to essay much more easily. Again it’s so interesting to find someone else with a similar experience.
Thanks for sharing! I think it is important that these individual processes are made visible. I currently see a lot of gatekeeping and blanket refusal of anything AI. This is not helpful as it drives every legitimate use of AI underground.
Really useful description of your process, and quite inspiring (although also left me feeling exhausted!) Lots of parallels here with my own approach to AI assisted writing, although interestingly having co-authored an AI-assisted book (for very intentional reasons) I find myself valuing my own craft of writing more and more. And so it's doubly interesting that this human craft aspect also comes through in your approach
Thanks! This is still a time consuming process. But for me it speeds up creating a text considerably. I went from being able to create about 1k words a day to about 10k.
This was very long but I read the whole essay. I kept finding myself thinking, "yep" both as an assisted writer myself, and as a writing instructor. I appreciate how you articulated your process. You gave me a lot to think about and some things I want to try.
A thoughtful article. Thank you for sharing your process.
I briefly toyed with Claude-assisted writing for my posts. It was better than what I expected, but still brittle enough to be caught by a keen reader.
Now with these prompting strategies, I will attempt it again. Thank you for this wonderful piece!
Thanks!
I find that using AI as an editor and repository for knowledge is empowering to the average citizen. Used incorrectly, it leads to incomplete thoughts and stale production. But used correctly it broadens our horizons and builds on the ability for normal people to write better without an editorial or research team.
I thoroughly enjoyed the article, and use AI to check my spelling and grammar when I am writing. Grammarly in particular, and when I need to flesh out an idea, or write in my native Scot's dialogue, I will use ChatGPT, mostly to check the sentence construction and other grammar related things. Sometimes it help me form what I am trying to say too.
Now a little bit about my background. I missed a lot of school due to illness when I was a child. From age 5 to 12, I was in and out of hospital, which meant I missed a lot of the formative years of Math and English. It's only now, at 42, that I can really say my math is where it should be, but for some stuf, without a calculator, I'd still be lost.
When it comes to English, I've had to fight through years of being told, your writing is terrible, you don't know how to use punctuation, that's not a paragraph... you get the picture.
What AI has done for me is open a door. A door that I can walk through and build my confidence, it can coach me on writing and grammar, punctuation etc, and explain why x is better to use than y. Could I have paid for a tutor, possibly, but when I work as much as I do, finding time is nigh on impossible, but again, AI has given me a way to tell my own story.
Again, as many of you will see, this post is done without AI assistance, and you can see how poor my grammar is, but, quite honestly, I don't really care. Because like you , Michael, I have found that I like to write fiction, I absolutely love world building and letting miy imagination run wild.
Anyway, thank you for writing, and showing the positives of your process
I loved this article! What interested me is that I can often tell on Substack when an author has used AI because of the usual "tells" (which I don't mind as long as their ideas are interesting), but with this, I honestly would never have known. You have a very clear and distinct voice that I found engaging and valuable to read, and clearly you have learned how to prompt.
Thank you for pointing out the ways in which AI assistance can boost not only one's critical thinking, research skills, etc., but can also increase a writer's confidence. While I am coming to this topic from the creative writing side, many of the same points you made are equally applicable there. Brainstorming and editing with AI have made me think in new ways, and consider new perspectives, that I wouldn't have encountered without it.
As a fellow neurodivergent, albeit one to whom writing has always come easily, I am fascinated by hearing from so many neurodivergent people that AI has finally enabled them to make their thoughts cohere. I wonder if this is less an issue of our thoughts cohering, and more an inssue of our thoughts not making sense to neurotypicals? One example I saw recently was an ADHD writer who would get frustrated because people seemed unable to follow the points she was making. She could clearly see the connections between them; neurotypical readers could not. Was this a failure of her writing, or merely a cognitive difference making neurotypicals unable to follow?
Thanks for the kind words. I think there are a great many neurotypical misconceptions. For example, I can’t take notes because if I do I can no longer follow what I am supposed to take notes about. I find it fascinating that the conversation about AI has surfaced so many supposedly critical skills that many neurodivergent people find to be a hindrance rather than helpful.
I’d prefer to read from someone who learned how to think versus learned how to prompt!
They're not mutually exclusive! Yes, AI can be used to outsource your thinking, but there are ways to use it that improve your thinking. I'm using it to analyze my writing, improve my French, and double check my analysis of my library's circulation to identify trends I didn't catch. You don't have it surrender your critical thought when using AI, and that's what I try to impart to my students.
Sorry, your "outsourced" thinking and analysis is based on research, writing, and decades of work from people like me stolen by tech companies, digested in data centers that consume environmental resources, through the efforts of exploited workers. That will be a hard no.
In terms of trends, perhaps check out this report:
Unlawful by Design: Exposing the Human Rights Costs of Generative AI
https://www.amnestyusa.org/reports/unlawful-by-design-exposing-the-human-rights-costs-of-generative-ai
I’m aware of these things, and I have thought a lot about all the points you mentioned. But I’m a school librarian, and my students are going to use AI regardless. I’d rather model for them the most ethical ways it can be used rather than leaving them to muddle through it unguided (which will inevitably mean they’ll use it to cheat). I don’t have the choice not to grapple with it in my work.
I also believe that, since it isn’t going anywhere, I should try to influence how it develops. Which, again, means showing people how to use it for things other than putting in some ill-considered, poorly written prompt and accepting the first output as gospel. As I said before, there are ways to use it that can augment and improve your critical thinking.
I love this article and I'm going to refer to it in my next article
Thanks, much appreciated!
Here is the article.
https://makingsensewithai.substack.com/p/im-begging-you-dont-listen-to-bret?utm_source=share&utm_medium=android&r=9b5em
Thanks for sharing your process. Very interesting. I'm still in the first phase =>
"Whatever flows from my mind gets written down regardless of semantic elegance, grammatical correctness, or stylistic coherence."
😆
😂
This is very similar to my flow with AI.
I have very similar experiences. Sadly, the moral case for AI assistance is not well understood or widely held. I have found my writing has improved significantly, whether AI-assisted or not. I think it could help many students who struggle with their writing to improve if used as you describe your workflow.
AI is starting to become mainstream. There was a bit of a backlash against AI assisted anything. But I am starting to see a lot of AI generated content in traditional media that nobody seems to be upset about. I think the relationship with that medium will normalize.
I write for law reviews. They are adding AI disclosure policies that range from acknowledgement of AI usage to outright bans. It's strange to me because I know that many faculty members use student researchers to draft substantial research memos, and colleagues make substantial comments. In legal practice, the question is who takes responsibility, not who drafts. So, I suspect there is some fear and protectionism at work. I recently saw someone on-line who found a hallucination in a paper and wanted to have the author backballed.
Thankyou Michael for sharing your method in such a detailed way. These honest accountings of human-AI collaborations are tremendously helpful. I have found the new models capabilities helpful in settling some challenges you have identified. For example Claude Fable can quickly set voice calibration skills and style guides (eg I now apply skills rather than uploading samples). Increased capabilities in terms of persistence between chats also helps (eg working in projects increasingly common across LLMs by various names). I have also found your suggested multi-model workflows valuable, particularly for verification, and am now developing various apps with Claude Fable for source verification (early stages). Thank you for sharing.
Yes, thanks for the comment. I have recently made a few changes to my workflow. One thing that I did is that I finally decided to work with Cowork rather than just Chat in Claude. I might write an update some time in the future.
Thanks Michael. I’d be interested in reading your experience with Cowork as i’m just about to shift to a sandboxed environment and experiment with Cowork and connectors.
I enjoyed reading this Michael and as a neurodiverse person too with a good part of my life in academia transitioning from idea to text would take me weeks of refining - whilst I watched peers conduct the transition in days, or hours.
I've noticed a similar process developing in my writing too. Exposure to new grammatical forms and combination of ideas. At the heart of it I decide ultimately, how the language is constructed, however AI help fold out some of my ideas!
I'll be trying out some of your process.
Thanks for the comment. I am still using pretty much exactly the same workflow although I have to admit that the latest versions of Gemini have a really good writing style for my type of content. It has become a viable option to stay completely within the Google ecosystem.
Great piece. Thanks for sharing your process and that’s a lot of back and forth between tools!
It sounds like your workflow is working but I’m wondering if you’ve explored trying to use Gemini ‘gems’ - inputting the writing guardrails you have to instruct the model how it should operate along with incorporating your research within a notebook from Notebook LM may allow for a one stop shop. Just some food for thought.
Thanks for the comment and suggestion. I have not yet used gems. I prefer engaging multiple LLMs in my process. But I’ll have a look. 👍
This is a powerful reflection on AI as an amplifier, not a replacement. Your process shows that judgment, creativity, and human discernment remain central, AI simply expands what you can achieve with them.
I talk about the latest AI trends and insights. If you’re interested in how AI acts as an amplifier for human judgment, creativity, and decision-making, check out my Substack. I’m sure you’ll find it very relevant and relatable.
I am amazed and thankful for your post. I have been using a similar process. I had also written a lot. Two books, over 90 articles. My writing was reasonably decent but I know writers. My mom is a writer. I was not a writer. AI assisted writing has liberated me, almost identical to the way it’s done it for you. I can go from idea to essay much more easily. Again it’s so interesting to find someone else with a similar experience.
Thanks for sharing! I think it is important that these individual processes are made visible. I currently see a lot of gatekeeping and blanket refusal of anything AI. This is not helpful as it drives every legitimate use of AI underground.
Really useful description of your process, and quite inspiring (although also left me feeling exhausted!) Lots of parallels here with my own approach to AI assisted writing, although interestingly having co-authored an AI-assisted book (for very intentional reasons) I find myself valuing my own craft of writing more and more. And so it's doubly interesting that this human craft aspect also comes through in your approach
Thanks! This is still a time consuming process. But for me it speeds up creating a text considerably. I went from being able to create about 1k words a day to about 10k.