I’ve been getting a lot of great feedback on my last post about building an AI model of my voice. One in particular surfaces a tension I’ve been having while working with generative AI.
Why would I want to create a model that knows how I write? I’m still confused as to the ‘why’ — drafting is an important part of the thinking process, working out how thoughts/ideas connect. I don’t want a machine doing that for me, because I might never come to those connections without going through this process.
This is a serious argument about what writing actually does. And it’s absolutely correct.
For me, writing is thinking. I think (and learn) through my writing. My writing (and thinking) are always changing. It changed drastically when I started blogging. It changed when I started writing with others. It changed when I started learning (and then unlearning) how to write for academic spaces. And now it’s constantly in a tug-of-war as I try to figure out how to make my work more approachable and accessible to others.
If you hand your drafting to a machine, you risk skipping the cognitive work that generates the thought in the first place. The struggle to find the sentence isn’t inefficiency. It’s often where the idea gets made.
I’ve taught writing long enough to know that. More to the point, I’ve also taught web design, coding, webmaking, and video production long enough to learn a powerful lesson. When you go into the process of making, writing, building, or creating, you never know what will come out the other side. There are certain things (affordances) that help or hinder you as you work and create. For example, when you’re writing, doing this is different in a Google Doc than it is on a typewriter, with pen/paper, or in Markdown. You’ll have different results and a different relationship with your own thoughts.
A typewriter demands a certain level of commitment; every keystroke is a permanent decision, forcing a linear, deliberate pace. Pen and paper offer a tactile, spatial freedom where arrows, margin doodles, and crossed-out lines map the messy geography of your brain. Google Docs prioritizes the social and the frictionless, where the ghost of a collaborator’s cursor or the safety net of “version history” encourages a fast, iterative flow. Even Markdown shifts the focus to structure and logic, stripping away the visual distractions of formatting to keep you locked in the “code” of your prose.
Ultimately, the tool isn’t just a passive vessel for your ideas — it is a silent collaborator. Each medium exerts its own gravity, pulling your creative process in directions you didn’t see coming when you first sat down to work. I’ve watched this happen with students for years. Give a kid the wrong tool at the wrong moment and the idea doesn’t just come out badly — it doesn’t come out at all. The gap between knowing something and rendering it into prose is where a lot of thinking happens. Close that gap too quickly, with the wrong collaborator, and the thinking doesn’t happen at all.
So yes. The commenter is right.
But here’s the thing: that’s not what I built ian-writer to do.
Stop erasing my ideas
I didn’t build it because I wanted to stop drafting. I built it because something kept erasing my drafts.
I’ve been publishing the Digitally Literate newsletter for over a decade. I wanted to get my drafts out of the older systems and tools that previously held them and archive them on my own site. As you can imagine, when you bring ten years of weekly writing into one space, you’ll get some drift.
I started using AI tools to figure out how to convert the files from HTML and other formats, strip out the unnecessary garbage, and archive them in Markdown. I wanted to identify a throughline that would include my ideas and voice, while also connecting themes and patterns across the individual issues.
As I engaged in this process, I kept running into the same problem. After every couple of passes through the issues, the AI model would sand something down. My voice would come back simplified, neutralized, and written in a way I would never actually write. Not wrong, exactly. Just not mine.
After a year of pushing back against that cycle of rewriting, correcting, and re-correcting, I started thinking about the problem differently. I wasn’t losing my voice in the drafting. I was losing it in the translation. Those are different failure modes, and they call for different responses. This was more than a problem of prompt engineering. This was a space of friction in my work, writing, and thinking. I was trying to identify and fight for my voice as a writer.
I think the commenter was worried about the first kind of friction. The productive kind, where the struggle to find words is also the struggle to find the thought. That friction is worth protecting. I agree. I have thoughts about that for an upcoming post.
What I was trying to fix was the second kind. Translation friction, where you already have the thought and lose it on the way to the page. Not because the thinking was incomplete, but because the tool that was shaping it didn’t know what my voice was supposed to sound like.
Imagine you’re painting a picture and standing in front of the canvas. You sketch out an idea and start painting. After some time, you step back to look at your work, only to realize that every time you turned your head, an invisible hand reached out and softened your brushstrokes. It blended your intentionally sharp edges into gradients, muted your boldest colors into “safe” neutrals, and corrected your perspective into something mathematically perfect — but empty. You didn’t lose the vision in your mind. You lost the evidence of your hand on the canvas.
I didn’t build a custom system because I was lazy or looking for a shortcut. I built it because I was tired of fighting an “assistant” that insisted on tidying up my messy, human truths. I needed a tool that functioned less like an editor and more like a mirror. One that reflected my specific jagged edges instead of buffing them away.
This distinction is vital for anyone worried that AI will replace the soul of writing. My work with ian-writer only ever touches the second kind of friction. The blank page still belongs to me.
Writing is a process
I want to be precise about what that means in practice, because I think most people imagine a different workflow than the one I actually use.
I don’t open a blank document and start writing. I also don’t open a blank document and ask the model to write something. In my work, writing is a process, and I’ve built up a system over the years.
My system usually includes a series of text notes I take in passing, or a voice recording while in the car. It includes the podcast I was listening to or the blog posts I came across online. And yes, it includes output from AI queries on a topic. All of this goes into Obsidian as a chaotic dump of half-formed ideas. I start teasing these apart and ask AI models to help me find patterns and threads in my thinking. What am I actually trying to understand in this work? How might I explain it to others?
When the AI model responds, I usually engage in a back-and-forth to better understand and push the thinking. Injecting friction into the process. If it responds the way we’ve all come to expect, a long laundry list of bullet points, hyperlinks, and ideas that have nothing to do with my actual question, I tune out and redirect or delete the chat. It’s frustrating. When it sends something back in a register that sounds like me, it’s not generating my thinking. It’s reflecting it back in a form I can work from.
The model never sees a blank page. It sees notes. What it produces isn’t a draft. It’s a mirror to help me clarify my thinking.
There’s one more honest piece of the workflow worth naming. Once I have a draft I’m satisfied with, I’ll sometimes run it through ian-writer as a final check. Not to correct my grammar, but to catch the places where I’ve drifted. Where I’ve over-qualified a claim into meaninglessness, conflated two ideas that needed to stay separate, or slipped back into the kind of academic register that loses everyday readers before they reach the second paragraph. Generic proofreading tools correct toward a standard that isn’t mine. This is a check run against my own established patterns. Not “is this correct?” but “is this still me, and will it land for someone who isn’t already living inside my head?”
That distinction doesn’t resolve every concern. The commenter’s worry about intellectual atrophy is real and worth holding onto. The risk of offloading too much, of letting the model close the loop before the loop is actually closed, is a failure mode I think about. The original post named this as the tics without the thinking. Close enough to be recognizable, wrong enough to be uncomfortable, and useful precisely because of that discomfort.
But building a tool to stop a specific kind of loss is different from building one to skip a necessary kind of struggle.
I was protecting my voice. Not replacing it.
Photo by Susan Wilkinson on Unsplash