Activity
Mon
Wed
Fri
Sun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
Jun
What is this?
Less
More

Memberships

AI Automation Society

409.1k members • Free

Clief Notes

39.1k members • Free

Old Me Living

290 members • $5/month

Real Men Real Style Community

13.6k members • Free

THE GRIM CIRCLE

1.2k members • $39/m

41 contributions to Clief Notes
Writing MD.files, What Do You Use?
What does everyone use to create markdown files with? I use LibreWolf as my text software and it doesn't. I know you can hand create in Notepad but I know there has to be a better option. I noticed that GPT seems to balk sometimes. I have it output the language for review, and then have it generate the md file. Last time I did, it mentioned that it doesn't exactly copy the review copy, just uses a summary of it. That didn't make much sense. Suggestions please.
0 likes • 15h
Thanks @David Vogel I'll definitely take a look at that. It sounds just what I need.
2 likes • 15h
That's close to what I'm doing @Johnny L . Lol, it must frustrate the AI sometimes. Just about the time we have a lot of work done, I take a break to actually go back and re-read all the output. I'm definitely the bottleneck in the loop. Larger term, I've always been the kind to want to open the hood and kick the tires. If I can understand the structure of a system, I can then know how to make the changes I need to get the result I want. With AI at least, you can ask it things.
Understanding Harnesses, A Question
I have a few questions to see if I've understood what harnesses are and what they do, and the roles of LLMs and other tools. When people say "I work with an AI", in general that just the whole field. When you get more specific, its that you have a collection of instructions, markdown files, databases and control mechanisms and thru that 'harness' various "AIs" are assigned parts of what ever I'm working on. I don't want my data and experience tied up behind a single provider, like many. I've looked at the equipment to host a LLM offline, and it seems stiff. Out of my budget. Here's the question, do we actually need the LLM offline? Or are we just going to need to maintain ownership of the harness components? If my orchestrater agent needs the research for a 1000 word summary I request, and calls my Chatgpt subscription for the searches, won't all the chat info stay on my machine? I almost have my mind around it, I think. What am I misunderstanding?
1 like • 1d
Thank you for the explanations @Aaron Klein right now I'm mostly focused on the basics of data, using folders and markdown files. I'm at least a year away from agents and by then, who knows what will change. I want to understand the underlying structures and processes before I dive in.
1 like • 1d
That does @Mira Bradshaw and it is much appreciated. I didn't understand the copies and the whole back and forth, but I'm not rabid about data and privacy. I can accept some leakage. But at 69, I'm old enough to remember when you couldn't take your cell phone number when you switched, and how the carriers had you locked in and paying what ever raise in rates they decided. I don't want to see the same thing with AI. But, I'm also using AI mostly as a research tool to write with. I don't need cutting edge frontier. Folders is the way I'm setting up my basic structure, so you may be correct that I'm envisioning more capacity than I'll actual ever need.
On the road to become AI engineer
Hello everyone, i m new here and since the end of my degree (comptability) I m really interested in AI et Angentic system, i m currently following the course too, but I had a question on the path I m going into, My objective is to become AI/Agentic engineer to be able to create automatic system for myself or for company and try to live with it, honestly i asked Claude a week ago how to do it in autodidact and he gave me a strong roadmap, i just want to know if its really pertinent and if any of u have some advice for my learning : 1) Learning Python (basic like being able to read it / debug / understanding environement / HTTP and JSON request / little project) 2) API LLM (prompt system, how API work, how to use it with JSON, make him use tool in a loop, manage API error and cost per call) 3) Agent & MCP (WorkFlow vs Agent, agentic loop, writing an MCP, real project) 4) Prod & Evals (Git, deploy something that work without me, Logs & monitoring, Evals to test and evaluate quality) And voilà that is my whole plan for the next 6 month, so if you have advice or see things that aren't coherent or other things to really learn feel free to tell me i take everything to learn the maximum and be able to really do something in some month 😄
1 like • 6d
You are quite welcome @Loïc Mora this is a great community and I'm glad you found my small contribution useful. I'm an edge case with AI. Most of you are looking at agents and software. I'm a writer, and using AI for deep research, synthesis and as a sparring partner for my ideas. Because so much of the data I want stored and have access to, is text and longer articles and extracts, folder are a good system for me. I'm in the process of customizing it for my needs, but even the basic setup Jake's tutorials will show you, are a powerful tool. More than just the data side, our ICMs and such ways to store projects, repos and experience, is going to become the new resume for workers. If you don't put together a AI resume, which you can take with you and show to new employers, then every time you leave a job, you'll be starting back at square one. At square one wages too. Employers are going to want to see your past work, and you prove you can do the job, while at the same time, they won't want you showing any of what you did for them to others, lol.
1 like • 6d
You never know @Loïc Mora when some custom bit of AI or software you made for your own business, won't be something others might want too. AI is moving so fast and taking so many twists and turns, we can't guess where we'll be in 6 months, let alone 6 years. And it isn't just cool tech that ICM stores. Honestly, it's probably one of the lesser reasons. Every small change you make to the LLM you are working with, every personalization or 'rule' for outputs, everything the LLM has learned that together makes you and it ten times faster, better, more productive, is YOUR digital advantage. Your Aston Power's 'mojo'. A well set up ICM preserves your data in a method which allows any of the tools like an LLM, to access it and then benefit from all that past experience too. Try to make any workflow you build, 'tool neutral'. Make it so you can swap them when you need to. Often you don't need a Fable 5 to do the job, maybe an older version of GPT will do it. Why pay frontier token costs, when bargain works just as well? Learn to know the 'particular traits' of the different LLMs and tools you use. I find that GPT does better at the academic research, and Gemini does better with the casual evening brainstorming stuff. Others have found that reversed. Again, this is a great community @Loïc Mora . I have no doubt that you will find what you need to learn here.
I'm flattered! And it's a great breakdown!!
Someone shared that a person a reaction video was made about my method and at first I was nervous but immediately it was amazing praise. I have never met with this person one-on-one and I haven't paid them or done anything other than post my own videos ! I think they do a great job at breaking some of the concepts down. It does an amazing job of breaking down some of the logic especially some parts where I go ranting in my video he slows it down a bunch ! Much needed
4 likes • 6d
@Nick McCashin here you go: https://www.youtube.com/watch?v=KPVaUuBkPz8 BTW, for future reference, click the video thumbnail, then when it opens here in Skool, go full screen with your browser and at the bottom right, you'll see a YT logo. That will open any video playing in a new tab at YT. That way you can save it to a playlist, or copy it. Welcome.
Clarifications about Folders & Agents
Hi everyone, I've been wrapping my head around ICM and agents. I'm a non-technical user even though I have a bit of background of workflow process engineering, and I'm still trying to understand what we were taught, and thought it'd be good to clarify with the community. When we build folders and sub-folders, can I say that the sub-folders are actually the "agents" that handle that part of the work? So if we have a content creation workflow, and research is a sub-folder, it is actually a 'research agent'. Is this understanding correct? So technically I can run hermes, claude cowork or goose cli on this folder, and it will react the same way (from the context and whatever is in the folders), is this correct? So technically if there is no requirement to have a build, it will just run as-is on the folders with no py script or type-script files, right?
0 likes • 6d
Welcome to the growing community @Pj Baumeister If you know how to run pipes and spot leaks, you'll have agent workflows down in no time.
0 likes • 6d
There are more reasons for me @Adrian Chen but others will mention them I'm sure. The other big one, I'm using AI with my writing, as a research tool for an eventual book. Making some sense of all the data and the process of writing require a lot of organization or you're screwed, lol. I use a similar system offline, so I understand it's usefulness.
1-10 of 41
David Trammel
5
341points to level up
@david-trammel-5293
Here to learn and here to help. I ran a resilient living website for 10 years. I go dark Monday afternoons (mostly). Say hi, and let's share ideas.

Active 4h ago
Joined Apr 30, 2026
Saint Louis, Missouri, US
Powered by