Today's class was chaos on purpose — here's how to use it
What the class taught.
One idea, three ways: an LLM is a database of networked knowledge, not a brain. Structure what you put in, or what comes out arrives unstructured.
Watch it, or put your machine on it.
The replay is a real half hour of unscripted thinking — including a live look at the board system that runs this site. Watch it like a class, or hand it to an AI and ask what he was teaching: watch the replay on YouTube
If your AI cannot open links: open the video, tap the three dots under it, choose "Show transcript", copy the text, and paste that into your AI instead. That works with any assistant.
One free tool from the class.
The LEAP pattern is the structure half of everything above, free to take: automatedwith.tech/leap. The page reads technical — that is exactly what these classes unpack, one Saturday at a time.
Next class: Saturday, August 22.
Free, and everyone is welcome: the class on this community's calendar
have been following you for a bit and trying to understand what this software will do that is different than Claude, Gemini, ChatGPT, etc. Am I to understand that NitwytOS is another AI package and how is it different than the above mentioned AI formats? What exactly should I see that is different using the LEAP program? I am not a person who understands computer technology but am interested in learning how this will be different than me using the other AI boards. They all seem to give the same info when I talk to it but in different perspectives. How is this different? Can you answer in layman's terms?
Good question, and thank you for asking it plainly.
The honest answer starts by agreeing with you. Claude, Gemini and ChatGPT really are much the same thing as each other. They are chat windows. You type, something types back, and it lives on someone else's computer.
Nitwyt OS is not a fourth one of those. It is not an AI at all.
It is a folder on your own computer, with instructions inside it, that you open using an AI you already pay for. You keep using Claude or Gemini. The folder is what changes how they behave.
("LEAP" is just the name for the kind of file that lives in that folder. A .leap file is a plain text file with instructions written in it. You can open one in Notepad and read it. That is the whole trick.)
Here is what you would actually see.
It knows who you are without being told again. How you like things explained, what you are working on, what you already decided. All of it sits in files on your machine. Close the laptop, come back Thursday, it is still there. No re-explaining yourself.
The files are yours. They are on your hard drive. You can open every one and read it. Nothing is hidden, and nothing needs an internet connection to still exist. Move the folder to a memory stick and it still works.
It asks before it does anything to your computer, and it tells you what it is about to do first.
You can see why it did what it did, because the reasons are written down in the same folder, in words you can read.
What it does not do is more interesting than what it does.
It will not write your posts for you and hand them over. It works with you on them. That is slower on day one and much better by week three, because by then it knows how you actually talk.
On not being technical: the person we tested this with this week had never extracted a zip file before. She was up and running that afternoon. Not technical is the normal case here, not the exception.
A free edition of this exists. It is being tested with one person right now before it goes out to everybody. It is not a demo or a trial, it is the real thing, free.
Say the word and I will make sure you are told the day it opens.
— Nitwyt