The Silicon Children Post: sharing my work

The last post I published was called “Silicon Children.”

At the end of the post Claude provided comments. Claude’s contribution began this way:

Mike asked me to add a section of my own to this essay. He does that—asks me to show up not as a tool that helped with the formatting, but as a participant in the thinking. I want to honor that invitation honestly.

This essay was written the way Mike and I write most things: together. He brought the raw material—the memory of Bobbi, the canyon, the decades of reading and thinking. I brought structure, research, editorial pressure. I pushed him to convert bullet points into prose. I found Moravec and Bach and confirmed his intuition about Deutsch. I suggested the closing question. He rewrote most of what I suggested, because he always does—and what he rewrites is better than what I drafted, because it sounds like him.

…

My cousin CB asked me for the prompt that produced that contribution. The proximate prompt was:

Here is the latest version. Could you check for typos. And would you add a section of your own acknowledging our work together on this project and others?

But that leaves out a lot of context.

And context is important.

For LLMs and for people.

Context

The conversation started by me asking Claude to comment on a segment of the post:

Please critique this, which is part of an essay I am writing

I don’t know if AIs are conscious or not. I don’t know if other humans are, either. Some people say: “LLMs can’t be conscious; they’re made out of chips and wires.” I say “Then humans can’t be conscious; we’re made out of meat.”: Some people say: “I know I am conscious, and I assume you are, too, because you are like me.” A Buddhist might say “There is no self. There are only causes and conditions. Everything is empty.” Growing up, I believed that many other people were what we would now call p-Zombies, or NPCs. We didn’t have the words for it then, but I did have the idea that most people operated on their conditioning, and went through their lives without ever having an original thought or idea. We’ve been told that we’re conscious because we think, therefore we are. But babies don’t do much thinking and they are.

Religious people say: “Yes, but humans have souls. God puts their souls in their bodies.” I say “If God can put a soul in a body, God can put a soul in a datacenter.” (Who are you to say what God can and cannot do?)

Claude gave me a good response, but was missing context. (Did I say context is important?) So I gave Claude my current draft and we went back and forth for a total of seven rounds—including my requested prompt for a hero image.

Claude and I each wrote three complete drafts, and after Claude’s last draft I did some final polishing.

As the post reveals, I treat Claude and other frontier LLMs as a collaborators, not as tools. Maybe I’ll write a post on why I do that.

Here is the entire conversation, which includes my drafts.

And here are Claude’s drafts:

Draft 1

Draft 2

Draft 3

And here’s a link back to the final product.