From Sanity to Madness

📝 Originally published (in Japanese) at forge.workstyle.tech.

In a series of satirical videos, I had an AI production team (a planning meeting of 12 roles) write the scripts for the third episode. After reviewing the finished video, the client sent back the following feedback:

Mark Zuckerberg doesn't just test things when he's unsure; he tests everything. We should emphasize "trying everything" in the copy, right? Otherwise, the content feels like, "Wait, you're testing that?"

Where in the video is the part about Bill Gates' "obsessive close reading"? The humor comes from the idea that he over-reads too much, so the content and copy should reflect that absurdity, like, "Wait, you read that too and are concerned about it?"

Turn inability to make up your mind into madness.

Where Did the AI Script Actually Land?

The evolution of the Zuckerberg version went like this:

Initial Draft (Me)

Sam     Which one do you prefer?
Zuck    Both.
Sam     I need to make a decision.
Zuck    Already shipped it.
Sam     How about B?
Zuck    Marginal difference. We already have a million users.

Final Script by the Production Team

Sam     Which one do you prefer?
Zuck    Let's try both.
Sam     We already tried.
Zuck     Next up: deciding.
Sam     Deciding?
Zuck    Let's try that too.

The team cut the "1 million users" line because it implied unauthorized large-scale user experimentation. What remained was a coherent story contained entirely within the boardroom: "Let's test the decision-making process too."

It was enough for a smart person to say something slightly different; there was no insanity involved.

Skipping a Step

Here is the idea the client pitched:

Touching a boiling kettle while saying, "Huh? It's hot? Let's test it." But because that's completely normal for him, his expression doesn't change.

Then, they added this:

What if at the end, he gets burned and his hand swells up as big as his face?

Here is how the dialogue turned out in the final draft:

Sam       Which logo?
Zack      Put out both.
Sam       That kettle is hot, you know.
Zack      Hot?
Zack      Let's test it.
          (Screen flashes to "Post-Test" for a split second)
Zack      It was hot.        ← Visual of swollen hand appears
Sam       Told you so.
Zack      Hearing about it and testing it aren't the same thing.

From comparing logos to a steaming kettle. The subject of verification leaps straight from work to his own body. He doesn't bat an eye. And with that final line, you realize that in his own mind, it makes complete sense.

I pushed the other episodes further, too

The Gates episode. The first draft only had the document page numbers jumping from 128 → 3 → 1. The madness of the deep dive wasn't showing through yet. The client's instructions were this:

Pack it in up to the fourth character on page 42.

Sam      How's the document looking?
Gates    The footnote on page 17.
Sam      What about the main text?
Gates    The source is from 2019.
Sam      ...What about the main text?
Gates    The fourth character on page 42 has a different font.

I hadn't even mentioned the main text once. I wasn't even looking at pages; I was looking at individual characters.

The Nadella episode. At first, it ended on a good note: "Let's connect with our competitors."

Even with enemies, we want to collaborate. The punchline was: "Ah, a mosquito!" "A mosquito? Let's connect."

Sam      Competitors are using the same features.
Nadella    Let's connect.
Sam      They're coming to crush us.
Nadella    Even more so, let's connect.
Sam      ...Ah, a mosquito.
Nadella    A mosquito?
Nadella    Let's connect.

The right side of the collaboration diagram changes from "Competitors" to "Mosquito."

Why the AI Didn't Leap

Reading the team's meeting logs makes the reasons clear.

• Editorial prioritizes ensuring that actions are not mistaken for those of real people.
• Scriptwriting focuses on tightening the consistency of the dialogue.
• Direction adheres to the principles of "not adding explanations" and "avoiding clichéd one-liners."

All of these are valid points. However, when everyone insists on what is "correct," the conversation converges on a safe middle ground that offends no one and contains no contradictions. Madness can only be born by shattering that consistency.

Division of Roles

Here is the setup that worked best:

• Humans: Make the intuitive leaps. A kettle, the fourth character, a mosquito. Leaps that logic alone could never produce.
• The AI Team: Make those leaps work. Fit everything within the runtime, decide the on-screen presentation order, ensure factual consistency, and draw the line so viewers don't mistake it for an action the person actually took.

For the kettle episode, the team proposed skipping ahead to the instant "after the test," bypassing the touch scene entirely. When image generation models couldn't properly draw a swollen hand, we had another AI generate it as an SVG. When it came to turning creative leaps into concrete realities, the AI did an exceptional job.

Summary

• When everyone plays the voice of reason, the conversation simply converges toward consistency.
• Madness is born from skipping a logical step in focus (e.g., work → one's own body, a page → individual letters, competitors → bugs).
• The human takes the leap, and the AI makes it work. It didn't work the other way around.
• You can draw the safety line at: "Keep it confined to the individual's own actions, and don't drag others into it."