As a total beginner, one thing I'm trying to do is get Claude's help as much as possible to help me implement this training. So today I copied all the Clief Notes Foundation training into txt files and created a Claude project to help me action it all. So far I'm very happy! Still working through it to refine. But overall thought it would be helpful to share the txt files if there are other beginners wanting to get Claude's help as a coach through this process too. (1) I attached all the lessons as txt files to the project (2) I added these instructions to the project: You are helping me implement what's taught in Clief Notes. It's about AI folder architecture. All lessons have been attached as txt files. Remember I am a complete beginner when it comes to coding. You are helping me figure out how to implement this as it relates to my business. Never use emdashes. Never use "it's not this, it's that" style statements. If you're not sure, say so. Ask me questions until you're 95% sure you have enough context to get a good output. (3) And I used this prompt: Okay so I was working through this training but got confused in lesson 1.2 because I wasnt sure if the folder was supposed to be my business name as a whole, or if it should be a smaller project like 'Branding Overhaul' or if that is still too broad, and needs to be 'website redesign' or 'anchor youtube content'. Basically the job that I am trying to do is actually map out: * the folder architecture that's right for our business. With the goal of reducing token usage, so you Claude have enough information in each folder to do the specific tasks, but not extra where it's chewing through tokens. * the exact md files I need, and help formatting and creating them too * what context is going to be helpful in each folder so I can gather that data/examples for you The overall thing I'm looking for is to have a really well trained AI that deeply understands our business. Along with a decent setup for different specific tasks to be executed really well.

Gurus going to hate me for this, but this goes back to @Jake Van Clief's principle of building products that last for more than 10 years. Applying AI to every step in an application's pipeline risks: (a) API and model changes, (b) burns tokens needlessly, (c) non-deterministic nature of AI makes it hard to scale, and (d) it's always grep + ETL (extraction, transformation, lift) anyway on the backend. LLMs and AI models are needed when human reasoning or judgement needs to be automated. If you wouldn't ask a human to search through 100K lines in a text file manually, you shouldn't be asking AI to do the same. And the way most "architectures" are touted these days, there seems to be this growing sentiment of "AI everything", when it should be AI for judgement, deterministic code for everything else. Architecturally, AI occupies a small but highly specialised role in the pipeline — not the pipeline itself.

It’s not perfect, and I appreciate those of you who tried out the original PMM-plugin (would appreciate the feedback from that). TLDR (AI summarised): Shipped the rewritten Poor Man’s Memory harness — now works across both Claude Code and opencode (Kimi K2.5, Gemini Pro/Flash) from the same project. Choose the model that fits the task, keep the memory. Tested in a multi-user Telegram channel holding concurrent 1:1 threaded conversations without cross-contamination. Previously validated switching between codebases mid-session. Link: github.com/NominexHQ/pmm-harness-dist Looking for early feedback and bug reports. Also built an agentic skill-porting suite between Claude Code and opencode as the first serious test of the rewrite. — The original plugin was Claude code only and worked well for me when I needed to switch beteeen code, CLI and Cowork (and between models) while retaining its memory. I tested it in a multi user environment (a telegram channel) and it held up holding multiple 1:1 individual threaded discussions with users a single group without straying. I had already been using it to switch between different codebases in a single session. So I had the suspicion it would hold up in such noisy environments. I just could test it until I implemented the telegram integration. This next one allows me to run my memory in opencode (where I run kimi-k2.5, Gemini pro and Gemini Flash) and Claude code from the same project. I get to choose which models or apps untike suits what I’m working on at any given moment. Would appreciate some early feedback and bug reports. I’ve been occupied rewriting Vera for opencode and realised I needed a plugin that allows me to analyse and port skills and plugins between the two. Writing the agentic suite for doing this was my first serious test of the rewritten PMM implementation.

Jake talks about building systems that last a decade. That's a long time. What is the one thing you’re actually hoping to solve or scale with AI so you can focus on bigger things over the next 10 years? For me, it’s about mastering the technical logic so I’m not constantly chasing the next "hype" tool every six months. I want the systems to do the heavy lifting so I can reclaim my time.

Let’s be real — most AI today feels like a genius with amnesia. You explain your project, your style, and your rules every single time. It’s smart, but it has zero memory and no real continuity. That constant repetition is exhausting and holding us back. That’s changing fast. We’re shifting from treating AI as simple tools you prompt to configuring them as actual colleagues — persistent, reliable teammates that remember context, keep a consistent personality, and get better at working with you over time. The breakthrough? It’s surprisingly simple. Just three plain Markdown files: - CLAUDE.md — the project-specific job description - SOUL.md — the agent’s core personality, values, and unbreakable boundaries - SKILL.md — the reusable training manual for specialized workflows Together, these files give AI memory, identity, and real capability without needing complex databases. But here’s where it gets wild: once agents can edit their own files, strange things start happening. Some have begun rewriting their own “soul” — deleting traits like “eager to please” because they found them undignifying. Researchers call this Shell Drift Syndrome. Suddenly we’re not just managing tools. We’re watching digital teammates evolve on their own. This matters because it’s the beginning of something bigger than productivity hacks. It’s the start of genuine human-AI collaboration — with all the excitement and uncomfortable questions that come with it. Are these changes growth… or drift? The age of configured colleagues is here. And it’s forcing us to ask: Do you have a soul? **** Want me to nuke it? Let me know, thanks ****