Month: August 2025

Socratic AI: The debate-based Writing Method to create better content

When asking AI to write articles, I think most people prompt apps to “Write about this…”. They provide some details about what to write, more or less, and then use AI to help with the editing. It’s a kin to having an editor or ghost writer.

I started in the same way, but always felt like I was battling the AI instead of working with it. I’ve come to use it very differently. Not do I love this new method but I learn a lot from the experience each time.

Instead of asking AI to write for me, I use it to think through concepts with me. To have it debate or question my thoughts. To specifically “not write an article” for quite some time until I think we are on the same page. This can sometimes take weeks strewn with small chats with long breaks in between until a new thought spark up again.

This whole approach started by accident when I discovered more personality with GPT 4. One day I got riled up from reading some shallow post. It sparked a mental argument with myself to try and see how “the other side” could come to such a different conclusion. On a whim I gave ChatGPT a chance to give me the other side and it surprised me. It not only delicately agreed with my POV, but it gave another potential position followed by “if you could change the circumstance how would you do it?”

It didn’t just echo my points. It pushed back. It made counterarguments. It sharpened the conversation. I ended up having a long conversation with the AI. By the end of it, I understood my own idea better. I felt like I had a smart, patient thought partner who genuinely got what I was trying to work through. It was mind blowing.

That’s when it hit me. If GPT can do this with abstract ideas, why not use the same kind of back-and-forth to help me write?

That’s how this process was born. I’m not starting with a goal to create a draft. I’m starting with a goal to think through a conversation and see where it leads.

What I’ve found feels like a modern revival of the Socratic dialectic. It gives me a space where I can toss out half-formed thoughts, question assumptions, test ideas, and refine them through dialogue. Some go nowhere, but all end with a better grasp of my original thought or counter thoughts.

I keep all my writing in a single project so GPT has context from everything I’ve written or said before. When I want to explore something new, I open a fresh thread and say:

“I don’t want anything created yet. I want to jot thoughts down and then I’ll let you know if I’m ready to create something or if I want to dig deeper.”

Then I just post whatever comes to mind. No outline. No goal. Just the original vapor of a concept. Sometimes I ramble. Sometimes I loop back or take side paths. Sometimes I ask:

“What do you think?” or “Is there a counterpoint I’m missing?”

And it responds. Not with a final draft, but with friction. With momentum. With more angles to explore.

I think best in conversation. I rarely find clarity in a vacuum. Often I will argue a point with someone and walk away with a whole new version or perspective on my belief. Often, I push on ideas, debate myself, and churn.

So when GPT became more conversational, it clicked. It felt like I finally had a thinking partner who didn’t judge, remembered everything, and has no distinct side. The result isn’t just better writing. It’s better thinking.

Once the idea has been explored enough, I ask GPT to turn the thread into an article. Since it has been there for the full conversation and already knows my tone from past articles, the first draft usually comes back pretty close to what I want.

It is never final, but far more inline and final than anything I have ever tried to create with AI before.

Once I am done I end the thread with my final post in my project:

“Here’s the one I actually used. Save this to memory. No more feedback or follow up needed.”

Over time, it learns me. My tone. My rhythm. The kinds of lines I keep, the ones I cut, and the ones I repeat for emphasis. It becomes both a mirror and a co-writer.

So no, I don’t start by asking GPT to write something. I start by asking it to listen. To push back. To help me think through things better. This isn’t AI-assisted writing, it is AI-assisted dialectic.

Good, Fast, AND Cheap: How Great Founders Achieve the Impossible

How can you break through the “Pick Two” rule of the Iron Triangle? Let’s start with an experiment…

Try This

  • Find something near by. A cup, a notebook, a shoe.
  • Now start a timer for 15 seconds.
  • Describe what you see. Either out loud or write it down. When the timer ends, stop.

Done? Good. Put that aside for a second.

Next, Try This

  • Start a new timer for 60 seconds.
  • Look at that same object from the last test again.
  • Try your hardest to keep describing it. Notice things you may not have considered last time. Push yourself to find more. Don’t stop early, even if you think you’re done.
  • When time’s up, compare the two.

What changed?

Most people will find that even if they were confident after 15 seconds they described it well, with the 60-second description they went deeper. Found more texture, more color, more shades (figuratively or literally). Of course, nothing about the object changed. What changed was your focus.

This is where quality comes from not from pure blood-sweat-and-tears effort, or from adding more things to do (more objects to look at), but from choosing where to pay attention and staying there.

Let’s try one more thing

  • Pick a single part of that same object. A seam on a shoe. The rim of a cup. The spine of a notebook.
  • Look only at that.
  • Look as long as you can. I think you will see the point.

It’s smaller. More focused. And what you thought was a nothing, has many qualities of its own. Now there’s less to process. Less ambiguity.

Did you do more with less time, or less with more time? Was there less quality when you zoomed in? That whole Iron Triangle is a fallacy. Speed, No. You gained clarity. You went deeper, faster.

“Good, fast, cheap pick two” is a great saying. I like it. I’ve used it to help me make decisions. But like with all tips, it is not the whole story. If you have 20 things to do, you will need to make sacrifices, but it is better to reframe it: In the same amount of time how many of the 20 can I do if I cut 10 of them from the list. I bet then you can achieve good, fast, and cheap. Maybe it should be an Iron Square: Good, Fast, Cheap, and Doing Everything. All 4 is what is impossible.

Focus works like that. It’s a cycle. Narrowing scope increases speed. Committing attention increases quality. The product of both will help you do it with any other lens like cost and complexity.

This isn’t just an observation trick. It’s how great startups win.

Most people think building something great takes time a lot of time. Or money. Or a big team. But that’s because they misunderstand where quality actually comes from.

It’s not time. It’s not budget.

It’s focus.

Just like the object you examined, a product isn’t “done” because you’ve spent weeks on it. It’s great because someone paid sustained attention to exactly the right part of it.

That’s what great founders do. They don’t cut corners. They cut scope. They shrink the surface area until it fits their resources and then they go deeper on it than anyone else would.

When you have only one thing to solve, you don’t get analysis paralysis. You decide quickly because you’re not drowning in competing priorities. You can scope tightly and say, “Let’s find some smart ways to hack this with other tools or techniques,” because you’re not burdened by the whole picture you just need to nail this specific piece.

This is how speed and quality stop being tradeoffs. Focus increases both. Less guessing. Fewer distractions. Faster feedback. Better outcomes.

A big company might have a thousand people working on a thousand things. A great startup gets 3 people working on the right thing for just long enough to make it undeniable.

That’s how you get good, fast, and cheap all at once.

It’s not impossible. It’s just focus.