Search results

I would quote Jurassic Park Your scientists were so preoccupied with whether or not they could, they didn’t stop to think if they should

Going back a few years now but I used to do three quite boring things: manually compare sitemaps and list what we both covered, only I covered and what I was missing. It gave me a good idea of where to expand and where to double down. I’d imagine this would be easy to do with AI. Use a XML to...

Anything Koray says. Just makes up terms for really simple ideas to confuse you

I raised a similar question the other day. I am looking at from the perspective of publishing to Amazon but don’t think it will be much different. I don’t personally care what the detectors say but I am concerned by the common traits and features that AI over uses. In and of themselves things...

I pay for Claude and Gemini and these are at the moment my go to. I like to brainstorm some other things with Grok if I am not getting anywhere with these two.

I have settled on a two AI set up. Ultimately Claude has the best prose and can be changed with the stylometry instruction. ChatGPT just produced one line paragraphs which read well but were horrible on the page. I have added an AI pass based on common trends and this helps clean the language...

Interesting I suppose the question is why bother? I dont think the general public is as bothered as we think they are. I haven’t seen an accurate detector yet.

So I can only say what I did a few years back. My blogs were all quite small based on PAA but I set up Etsy shops and did POD. I filled all my ad space on my site with my own work. So every sale was money for me.

I noticed this as well. One said 17% and the other nearly 100%. What I have noticed is that well edited work shows up as AI more than normal writing

I have found using a stylometry file really helps with with AI sounding natural although it doesn’t take away off the isms

Been doing some work on writing ebooks for KDP all with AI and the subject of AI Detectors keeps coming up. I have zero confidence in these online detectors that give a percentage score especially when I know where the work comes from. I find that having emerged myself in AI writing the...

So I have had a couple of experiments on the go at once. One dealing with the hallucinations and the other with the author. This is the output and I would be interested in people’s thoughts on it: Chapter 4 THE PARADOX OF CHOICE When Abundance Becomes a Weapon The art of being wise is the...

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...

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

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...

I remember reading about the reply guy method a few years ago and was intrigued by it. I have used a few versions of it over the years. I think getting in early on a conversation can be very beneficial but it’s a lottery as to which ones grow and become something. With a few different accounts...

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...

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...

I have been running some experiments in my journey thread and what I have come to realise recently is that one prompt doesn’t work. You are asking the AI to do too many seperate jobs at once. My hypothesis is that breaking it down into a chain of prompts will produce better results. So on a...

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...