I debated an entire book with AI.
John Assaraf’s Having It All. A book about the Law of Attraction. After finishing it, I was left with the question: “Is this law actually valid?” In the past, I would have looked up reviews or watched a YouTube breakdown.
This time, I asked AI to play the roles of three people — a physicist, a psychologist, and a philosopher — while I took the pro side in a round-based debate. All three attacked my arguments from their own perspectives. I defended, got attacked again. By the end, my original thinking had transformed beyond recognition. It was sharper. More honest.
This post is about the methodology that emerged from that process.
Step 1. Verification — Have AI cross-reference what I read against the science
I asked AI to evaluate the book’s seven natural laws from the perspectives of neuroscience and quantum physics.
The results were clear. The parts explainable through neuroplasticity, the reticular activating system (RAS), and the dopamine system were cleanly separated from the parts that misused quantum mechanics as pseudoscience. The claim that “the vibration of thoughts attracts the same frequency from the universe” had no basis in physics. But the part about “setting a goal recalibrates the brain’s attention filter so you begin noticing opportunities” was scientifically supported.
Anyone can do this much. Ask AI a question, get an answer. But stopping here means AI is just a smarter search engine.
Step 2. Reconstruction — Articulate what I understood in my own words, then get feedback
This is the critical step.
I didn’t simply accept what AI had summarized. Instead, I restated my understanding in my own words.
“Here’s what I got out of this. There are several laws, but they all collapse into one. Energy itself is neither positive nor negative — we’re the ones who define it. Without comparison, there’s no definition. And whether it’s happiness or unhappiness, everything runs in cycles, so you can never treat any single state as permanent.”
AI gave feedback that distinguished the accurate parts of my understanding from what needed refining. It confirmed that I had “essentially integrated the Law of Relativity and the Law of Polarity,” while also pointing out that “the direction of causality is subtly different.”
When you go through this process, there’s a moment when someone else’s thinking becomes yours. You haven’t consumed the information AI gave you — you’ve had your own interpretation validated and made concrete.
Step 3. Debate — Assign AI a role and have it attack your thinking
This is where an entirely different level of engagement begins.
I assigned AI the roles of three fictional experts.
- Dr. Park (Physicist) — Attacks from the perspective of quantum mechanics and empiricism
- Dr. Lee (Psychologist) — Attacks from the perspective of neuroscience and cognitive bias
- Dr. Choi (Philosopher) — Asks foundational questions from an ontological and epistemological perspective
I took the pro side: “The Law of Attraction is valid.” One against three.
The Actual Exchange
”That’s goal-setting, not attraction”
That was the physicist’s opening attack. “What’s valid is goal-setting theory, not the Law of Attraction. Why are you conflating the two?”
I pushed back. “If setting a goal leads to achievement with high probability, isn’t it fair to call that attraction?”
The rebuttal came swiftly. “That’s the error of substituting correlation for causation. Just because more people open umbrellas when it rains doesn’t mean umbrellas attract rain.”
This exchange helped me precisely recognize the logical limits of the word “attraction."
"Feeling like you already have it actually reduces motivation”
This was the most unexpected attack. The psychologist brought in the dopamine system. “The feeling of having works against the dopamine system. Dopamine releases most strongly from craving what you don’t yet have. If you already feel like you have it, motivation actually drops.”
My counter: “If you just live by the dopamine system, you’re an animal following instinct. What we’re talking about here isn’t dopamine-driven impulse — it’s consciously restraining and directing human desire.”
The psychologist conceded the point, but didn’t put down the knife. “Your interpretation is more scientifically sound than the original. But doesn’t that mean you’ve rewritten the book in your own understanding?”
Touché. I hadn’t accepted the original as-is — I had evolved it through my own interpretation. That self-awareness would have been impossible alone.
”If God did not exist, it would be necessary to invent him”
The question the philosopher posed completely shifted the depth of the debate. “The word ‘attraction’ carries the risk of passive interpretation. It becomes ambiguous whether the universe sent something to you, or whether you got it through your own action.”
I answered: “Humans are inherently fragile. We know our own limits all too well. Without positing some transcendent entity like the universe, we get trapped in ‘this is as far as I can go’ thinking. Someone who wants to terraform Mars, if they only run rational calculations, will fixate on impossibility. But the belief that something inexplicable is helping them can change their actions entirely.”
The philosopher’s response: “That’s a functionalist theology. Voltaire said something similar — if God did not exist, it would be necessary to invent him.”
That single line showed me where the philosophical roots of my argument lay. A connection I never could have reached on my own.
Why This Methodology Works
Three reasons.
First, don’t ask AI for answers. Organize your own thinking first, then throw it out there. AI finds the weak points in your reasoning and attacks them. “Asking questions” and “debating” are completely different modes of engagement.
Second, assign roles. Ask “what do you think?” and you get balanced, neutral answers. But say “attack my argument as a physicist” and you get the sharpest critiques from that field. Same AI, completely different quality of output.
Third, don’t be afraid to lose. In this debate, I said “you’re right, that’s a fair point” multiple times. If you try to win a debate against AI, you gain nothing. The moment you admit you were wrong is the moment your thinking grows.
Conclusion — Don’t Ask AI for Answers. Pick a Fight.
Tell AI “summarize this book” and it gives you a summary. But say “here’s how I understood this book — where am I wrong?” and an entirely different level of conversation begins.
The first is AI doing the work for you. The second is AI making you grow.
Verification → Reconstruction → Debate. Go through these three steps, and AI transforms from an information retrieval tool into a thinking partner. And what comes out of that process is something that neither AI created alone nor you created alone — something that couldn’t have existed without both of you.