Chapter 4. Where the rules come from, and how they were tried
Who tried them
AI helped with this work. I will say so plainly. I did not do it alone. But a human, me, made every decision about every status.
I know how that may sound. In chapters 1 and 3 I warned you about smooth AI answers. Then I used AI to test my rules. So hear what the AI did, and what it did not do. It read, it objected, and it sorted. It never set a status. Nothing it said settled anything by itself. I made every call, and I ask you to check me too.
Here are the jobs the AI did.
A blind reader is an AI in a fresh chat. It has no memory of why the rules were written. It is given the rules and a set of cases. It is not told what answer is expected. It reads, and it reports what each rule gives.
A skeptic is an AI asked to raise the strongest objections that one view would raise. It speaks as that view's written paper records it, and never as a person. It may not invent a quote. Where the paper is silent, it writes no position. I name no view and no person in this book.
Other AI helpers sorted what the readers found, and marked each objection against the rules. Then I answered the open questions. A mark is never a verdict on a view or on a person.
What did the skeptics test? A long paper of mine. In it I apply these rules to Jesus' talk on the Mount of Olives, and I set out how I read it. In this book I call that paper the long argument. This book does not argue it. Here I take no side on what that talk means. The rounds on the long argument test my long argument. They do not test the Bible.
AI also drafted wordings, edited the long argument, and ran scripts that check quotes. I kept notes on all of it.

