I made this book in one long session with Claude Code (a coding agent that works in my files and my terminal).
Finding the book's material in my chat history
help me work on publishing a book around our field notes from a centaur ;;
I checked the repo. The plan is in place and nothing has started yet. […] The edit work can't make the route decision for you.
Decide the route
So most of my conversations are actually with ChatGPT. How can I extract those insights or real experiences from my GPT? Is it something you can help me with by looking at the ChatGPT client on device?
Yes, I can help. The ChatGPT app is not the way in, though. You already have a better source on this Mac. […]
Yes, mine it
help me ask gpt for such examples for book via prompt
Paste this into ChatGPT. […]
ChatGPT sent back fifteen episodes from my history, and the agent checked them against my export.
Lead with this: the book's current text began as ChatGPT guessing how you use it. […] The same day you compared its entries with your own newsletter text, and the newsletter text was better. […] Not found: "everyone a builder" […]
since 90% of my ai work is with YOU claude code how can we learn from that to inform the book meaningfully
Short answer: right now the book under-uses this, and fixing that is the most meaningful lever left. […] So the book tells mostly the chat-era story, while your actual practice moved to agents.
Yes, include [my Mac mini]
Most of my side of the session looks like this. The agent ends each step with one question and a button, and I press it.
Yes, draft it
Good, put it live
Yes, do Creating
Yes, draft it
Yes, put it live
Yes, do Building
I've started five searches for Building cases: three over your ChatGPT history, one over your Claude sessions and repo rules, and one over the newsletter […]
Over the whole session the agent started more than fifty other agents, many of them searches through my old chats.
Making the book's text my own words
where can i see these, how do we make the whole writing personal, real, mine
[…] the prose is built from sentences you already wrote or said: newsletter text, your talks and calls […], and your own chat messages. My words appear only where the text needs a join, marked [with double brackets] in the draft so you can see every one. […] Honest point about chapters 1 to 3: they are live, but the prose is mine, with your quotes inside it.
In my local preview the marked lines show in grey, so I see at a glance which words are not mine.
"The newsletter issues from 120 on are excluded, because ChatGPT co-drafted them." not true for all where did u learn that?
I overreached. The evidence I had was narrower […] Nothing at all supports "from 120 on". I made that up as a rule.
Then it checked every passage against my old chats, to see who wrote it first.
Lead with this: some text I had treated as yours turned out to be ChatGPT's. […] the issue 120 opener ("This newsletter began as an attempt…") first appears in a ChatGPT reply, so it's cut.
The same check ran on the notes for my talk.
The agent found that much of your […] slide notes was ChatGPT's clean-up. It used none of that text. It used your raw talk, which you had pasted into ChatGPT, instead.
Choosing images for the book
imagery: how do we enliven it
real artefacts get boring. generated images can look generic. artistic svgs are difficult to look good. what cna we consider if anything.
On imagery: you've named the three usual traps. What's left is imagery made from what only this book has: your words, your data and your own type. […]
Conversation shapes + Octa
Octa is the Envisioning typeface. The shapes drew each chat as bars, my turns above a line and the model's below it.
oh dear the expanding titles in octa 100% dont work
and i meant 1 illustration per chapter, not one per example
the examples need to look more like chat exchanges tho
i dont like the octa font here
Octa is out. Chapter and card titles are back in the site's own Ubuntu Mono, as before. […]
Yes, merge it
the 'graphs' dont add anything, conceptually, imo
the histograms up/down dont teach me anything, nor are they distinguishable
Agreed, and the shapes are gone. […] The chat exchanges stay.
cover: yeah help me design smth pertinent as code. think stripe books imprint.
hmm, good start with cover but too terse imo, think business books. but IT'S GOOD.
I redid the covers in a business-book layout. […] The title is the cover.
cover: dots: make variations of it. idk about all colors switching on the same column maybe vary it
and delete the other cover directions plz
[…] ragged: each row switches at its own column, so the edge is uneven.
dots-ragged is the one
the 'book cover' bleeds into the background deosnt look like a book cover tbh
The cover's ink colour is the same as the site's dark background, so it melts in.
Removing lines that sound like AI
these subtitles are so claudish i dont want them "Who wrote it, how it was made, and who to thank"
this is claudish "This chapter is about coding agents: what I handed over, in what order, and what I kept."
Card subtitles are gone from all chapters and both drafts: all 85 of the agent-written morals under the card titles, like "When it disagrees, listen." […] Delegating still has 57 lines an agent wrote, and they'll keep reading like that.
Yes, strip them
I stripped them. The Delegating draft is now only your words, with no [marked] lines left. It went from 3,322 to 2,027 words.
lets augment with my talk later but keep claudisms as containt as possible for now. leave an issue for me.
Keeping only the best conversations
how do we 'simulate' epub/kindle to get a sense for how ready the book is? its too short i think.
You're right, it's short. […] As a short read it holds up. As a full book it is thin.
more cards: even them out yes
ok, for the book... what makes it good and useful for people? […] how do we show just hte best convos not SO many
[…] You're right: 12 cards per chapter plus the chats in each essay is too many. My earlier move to even them out solved the wrong problem.
Yes, rank them
Yes, apply it
[…] The book is now about 12,700 words, roughly 50 pages. That's honest: it's the best material, not the most.
and chapter for Principles: dont make it 7, make it open, and help me find more idiosyncracies about how i work (liek not spelling properly)
The chapter is now called Principles, with no number […]
feel to include many
the 'principles' are undercooked. have a subagent review them, give each example a descirpiotn paragraph, a good/consistent title, togetier with the chat examples? so each principle is a principle/block?
[…] It will also merge entries that are really the same principle […] and drop weak ones.