[Journey] Creating Good Books With AI

rexant said:

No bro, same like mugs and tshirt bro, you need a supplier for printing
I've uploaded the books 2 months ago and all made by AI

Click to expand...

Sorry to hear about the books. It doesn’t seem that KDP is as easy as people make out. Did you follow any programs?

Etsy is great in the right market and niche. I mainly target woman and a sub niche within spirituality.

rexant said:

I will focus on the quantity and going to upload more, hopefully I will get some profits
You're right, Etsy is better, you making good on POD mugs bro ?
I plan to make some journeys with POD(tshirt) on Etsy

Click to expand...

Mugs are my full time income. KDP is a side interest at the moment.

I have another product I am looking to launch later this year which is POD but if it works I will transition to holding stock. Thr market up is ridiculous compared to POD on this one.

Never done the tshirt thing. Are your books and Etsy linked or completely separate

My other books arrived and I think I have found an author I really enjoy reading Erik Larson does this creative non fiction. The Devil in the White City was a really interesting read. Not sure if there’s any practical implications for writing Good books with AI.

One thing I am going to try comes from two different sources. One guy whose name I forget talked in a podcast about every page needs to earn its place in the book. I think that’s gold. I am not sure on how to implement that just yet but it feels right.

I think in someways this may tie into what Dean Koontz does with his heavy editing and reworking of every page before he starts the next. He’s a fiction writer so it doesn’t quite translate but I think that’s a way of improving a chapter.

I think I had a bit of a eureka moment today when YouTube played a random video on a phd level paper.

It got me thinking about the process of writing and so I went across to several AI chatbots to see what they would say.

The consensus was that to write a book or chapter AI has to:

1. establish the book premise,
2. understand the target audience
3. address the book purpose
4. research the subject matter
5. select what needs to be include,
6. develop a chapter skeleton
7. select a voice and tone
8. write the the chapter

The end result is that I think asking AI to write a good book or even a chapter is too much in one pass.

I am starting to wonder whether one brain for one task might be a better option. Ask chat got to research the subject first then write based on that. I guess in someways this is closer to what a human would do.

I don’t know but it’s an exciting thought and feels like my first move forward

After my last post I wanted to test whether breaking the writing process down into separate tasks helped produce noticeably better output.

For this experiment I want to do a single variable test.

The first experiment which we have done before was simply a one and done prompt Prompt: One-shot “Write a 1,500-word book chapter on saying no for a book on “people pleasing”

Then a simple structured Multi-Brain Sequence split into two prompts:

Prompt 1: Research and summarize key points, statistics, examples, and common pitfalls on the topic.

Prompt 2: Using only the research output above, write a 1,500-word book chapter on saying no for a book on “people pleasing”

So the second prompt in experiment 2 is deliberately the same as in experiment 1 but with the confined of using the research in prompt 1 of experiment 2.

I ran everything in incognito to avoid any carry-over from previous chats.

The multi-brain approach produce a much better book chapter. Notably so.

In case this was a fluke I repeated the experiment a further 11 times and consistently the multi brain method produces higher quality results.

The multi brain method versions felt like they flowed better were more specific (even directly referencing some of the research)

Now to be honest it’s far from perfect. The voice issues are still there it still reads like AI but on a side by side read there’s a clear winner.

I feel like this is a much needed win. Having listen to so many people on YouTube and social media on how easy KDP is I honestly thought I would have at least a draft of a book by now.

For now I am going to put a tick next to multi brain. Next I’m going to expand this into a longer chain and see if there comes a week point. Context window may come a problem but we will see.

Has anyone else experimented with prompt chaining like this would love to hear your experiences.

So I think I have an idea to test based on multibrain and it goes back to the books I bought earlier.

One book I liked was Brainfluence and I have kept going back to it. Perhaps to write a good book I shouldn’t be writing a traditional non fiction but rather a modular or listicle style book.

Use the multi brain technique on each chapter and end up with x amount of smaller chapters that each cover one topic.

To my mind that gets the best out of AI minimises the issue with context windows and should produce a book of substance.

I've written some long form books and Ai does best when its given a structure to follow, even then it needs heavy refining afterwards. Took me a few hours to get like 120 pages even readable to a normal person. And then a few more days in editing and changing sentences to get it somewhat okay. You also need to distill a writing style down into a prompt and give it examples to write like otherwise it just drifts into repetitive nonsense. Good luck!

Best of luck to you

Hamoudi34 said:

I've written some long form books and Ai does best when it’s given a structure to follow, even then it needs heavy refining afterwards. Took me a few hours to get like 120 pages even readable to a normal person. And then a few more days in editing and changing sentences to get it somewhat okay. You also need to distill a writing style down into a prompt and give it examples to write like otherwise it just drifts into repetitive nonsense. Good luck!

Click to expand...

I have noticed in my AI experiments so far that the flow of sentences doesn’t follow a logical or sequential pattern. For those into theology it’s a Markian sandwich. Here’s A here’s b and here’s A. Interesting and not obvious choice by the machine.

I do have writing style to complete later on but I agree it’s vital and not just putting in the style of or inspired by x. I like the idea of al lay creating an avatar for the author beyond just words they use. This is for further down the line

What did you end up doing with your book(s)?

I'm not sure AI can write a viral book because it doesn't have a unique character (yet). However, you should write the book for yourself. If you can't stop reading it, then it's fine.

MasonBookwright said:

thank you I appreciate your response and I largely agree with what you are saying - there is a ton of slop out there.

I can well believe 99% of people using AI to publish are slapping a generic prompt into ChatGPT, and dumping an unformatted PDF straight onto Amazon expecting to make millions overnight.

But just because the market is flooded with bad AI books doesn’t mean you shouldn’t use AI. It is like saying you shouldn't build a niche website because there are tens of thousands of crappy WordPress blogs out there.

But that’s exactly why I started this journey.

I’m not doing a "one-click" spam method.

I want to see what AI is actually capable of. Through trial and error can I get AI to write a good.

If I can’t I won’t publish anything.

Click to expand...

It means that you edit the book manually yourself right? You can't completely let AI write the whole book without a human touch. Keep us updated, Best of luck!

Pluncray said:

It means that you edit the book manually yourself right? You can't completely let AI write the whole book without a human touch. Keep us updated, Best of luck!

Click to expand...

That’s an interesting question and I am not sure I have an answer at the moment. I have been primarily focused on creation up until this point.

Thinking off the top of my head I envisage that there will be some AI assisted editing followed by human input.

For the ai assisted I can see the multibrain concept working. Having an AI as a line editor, a development editor and later a proofreader.

The amount of human input will probably depend on the final creation methodology.

So if I end up going with something similar to Koontz method then there is a lot of drafts and redrafting going on. Issue that would be picked up in a normal first edit will have been tackled before hand.

If I go with first draft first kind of method then there will be a heavier editing process. It’s on this I could see multibrain then human editing being needed a lot more.

MasonBookwright said:

That’s an interesting question and I am not sure I have an answer at the moment. I have been primarily focused on creation up until this point.

Thinking off the top of my head I envisage that there will be some AI assisted editing followed by human input.

For the ai assisted I can see the multibrain concept working. Having an AI as a line editor, a development editor and later a proofreader.

The amount of human input will probably depend on the final creation methodology.

So if I end up going with something similar to Koontz method then there is a lot of drafts and redrafting going on. Issue that would be picked up in a normal first edit will have been tackled before hand.

If I go with first draft first kind of method then there will be a heavier editing process. It’s on this I could see multibrain then human editing being needed a lot more.

Click to expand...

Alright, there's no problem. You can do whatever you want provided that you get the sales volume that you want. Best of luck!

Pluncray said:

Alright, there's no problem. You can do whatever you want provided that you get the sales volume that you want. Best of luck!

Click to expand...

Thanks as I say I do t know yet with regards to editing. Open to suggestions and ideas.

I ran the modular / listicle test I mentioned last time by doing the following:

• Chose a narrow self-help niche
• Used the multi-brain method (research pass → writing pass) on each individual section
• Aimed for short, self-contained chapters/sections so I could avoid context window issues and keep quality higher on each piece
• Fact checked with different AI’s

It didn’t work as well as I’d hoped.

The individual sections in isolation were okay. They were clearer and more specific than my earlier one-shot attempts which I still see as a win and could be the basis of something. when I put the chapters together and read the whole thing as a book, several problems became obvious:

Many sections felt padded. Paragraphs or saying anything.

The information was surface-level once they were next to each other. What looked decent on its own started felt repetitive over 100 chapters.

The book ultimately felt more like a collection of blog posts than a cohesive piece of writing. There was no sense of progression, purpose or transformation.

Even with the multi-brain approach, the tone drifted between sections. It’s like different windows had different AI personalities in it.

A lot of the “research” AI pulled was the same well-worn studies and examples that appear in every book in the niche. It lacked the sharper, more original insight I was hoping for. It doesn’t even have to be new insight but it should feel that the author has somehow lived it.

In short, the modular structure helped with some technical problems (context window, focus) but didn’t solve the deeper quality problems. It just packaged them differently.

I’m not writing the format off completely I feel like there is something there and books like Brainfluence and Cashvertising prove the format. The question is can AI do it.

It hasn’t all been a complete right off. In my experiment I noticed that even within the confines of multi brain there was still room for hallucinations.

Thanks to a random youtube video I came up with a workflow that I think may solve it thanks to some recent changes in AI.

I now aim to create a test loop on a subject I know. If I can eliminate the hallucinations before the edit that’s a big step forwards