Everybody's a builder now. You open Claude Code or Cursor, noodle on a prompt for twenty minutes, and by Sunday night you've got a working app with auth, a database, and a Stripe checkout that actually processes a payment. I've done it. You've probably done it too. The first time it happens you feel like a wizard. And then the silence hits. You post it, you tell a few friends, maybe you drop it in a Discord... and nothing. Not "this sucks" nothing. Just nothing. No signups, no comments, no [censored] given, LOL. That silence is the lesson. And it's the same lesson that's existed since the first person built the first piece of software, it's just louder now because building got so cheap that everyone's tripping over it at the same time. Here's the thing nobody wants to hear: writing the code was always the easy part. Even before AI, a decent dev could smack out an MVP in a few weeks if they knew what they were doing. What separated the businesses that made money from the ones that didn't was never "can this thing technically function." It was always two other questions. Does anyone actually want this. And will anyone find out it exists. AI didn't change that equation. It just deleted the excuse. Ten years ago you could tell yourself "well, building takes so long, once I ship, people will obviously flock to it." Now you ship in a weekend and get to watch, in real time, that shipping was never the bottleneck. The market doesn't care how fast you built it. It cares whether it needed to exist. I think of it like the crepe analogy I keep going back to. Your first crepe is trash. Everyone's first crepe is trash. But with vibe coding, people are getting a hundred crepes an hour now instead of one a day, and they're shocked that crepe number ninety-four is still trash if the batter (the actual idea, the actual customer, the actual problem) was never right to begin with. You can iterate on execution speed all day. Speed doesn't fix a batter problem. So what's actually hard, if it's not the build?

I've just had the most amount of hallucinations ever in one session. My model is completely making shit up. I have no idea where is this coming from, because I have not modified any of the foundational/instruction files or changed my processes. It's undertaking tasks or modifying files in ways I didn't ask for and it seems to be 'assuming' what I want instead of listening to instructions and its constantly forgetting context now. I'm thinking of removing and reloading Claude Code too if its a potential caching issue similar to the old 'memory' files issue I was having where it was generating custom instruction files outside of our working directory which were negating my claude.md, etc. Anyone else seeing issues increase lately?

Looking for people's opinions on something - please speak up. I am blessed to have a handful of high-end professionals that I can discuss AI with. I suppose I use them to help me sharpen my growing spiel for AI, and they likely trust that they are learning something along the way. There is a part where I want to guide them into a place where it is obvious to them that sometimes an LLM alone cannot provide a full level of expertise, and people will have to augment the LLM. Here is the example I use. I say, quite honestly, that I would 100% trust an AI to give me a few home exercises for my two 10lb weights, as an ankle sprain is keeping me from running. I trust any LLM to summarize that for me from the LLM's transformer training. Then I say that I think it is obvious that a third year NBA player would be crazy to ask an LLM, 'I am a third year NBA player going into the final year of my rookie contract. Please give me a summer workout plan before training camp starts in the fall.' - well, maybe not crazy to ask, but crazy to follow that advice without any other input from trainers, his NBA team, etc. It is supposed to be a fun example that guides the conversation into what do you or your company do that is unique and to begin the discussion about methods to add their expertise into their operations. And it worked a few times, until tonight. A high end real estate executive asked me, 'don't you trust an AI to summarize a workout plan for an NBA player?' I thought the answer was an obvious no... but perhaps, live and learn?? I guess I am asking for advice on two things. (1) Do people trust an AI to give an NBA player a workout plan. And (2) How do I fix my example/spiel. I don't want to talk about NBA athletes. My desire is to get people to talk about what they do that is unique and how AI (okay, ICM) can help them. I don't mind a bit of failure, but failing twice in one sentence has lead me here to ask for advice.

Im one of those people who need a project to properly learn a new skill like all this icm and folder methodology. Im a relatively new to AI but not python or technology. I’ve been in the VoIP space for over 20 years. Any suggestions on something I could build or help anyone out with so I can get fullly immersed into this system ?

This post is not for the ICM pro, there will be no talk of gates, scripts, or orchestration! This is for the person just starting out! @Karli Rosario Yes, I mean you! (And anyone else who may just be starting out with ICM) Seriously, I'm glad you found ICM. Let me give you the simplest version of it I know. ICM is a system of structured folders. Yes, the same folders you have been using on a computer for most of your life. The ones you stored photos in, & pirated music from Napster and LimeWire. That's it. I will take you through the process below. When working with AI, a lot of people are doing this 👇 You take a long prompt, feed the entire thing to AI at the beginning of your interaction, and spend time going back and forth with AI trying to get the outcome you want. (I'm not coming for you Karli, you are exceptionally good at this, but ICM will make your outcomes exceptionally better!) What is different about AI and prompting with ICM 👇 You take that same really long prompt and instead of giving it to the AI all at once in the beginning, you break it into steps, and each step gets its own folder, each folder gets its own piece of your large prompt, just 1 step from it, and you ordered the folders by when the steps happen in the workflow. You got it? Good 😊 ❤️‍🔥 -------------------Still a bit unclear, let's bake a cake. 💡 Here's an analogy I have success with (I picked this up way back in my VB programming days): Imagine teaching AI to bake a birthday cake. 🎂 The way most people do it: 👇 One giant prompt. "Bake a cake, here's the recipe, the frosting technique, the decorating style, the candle placement..." Then they hit enter and wait. The AI is juggling 40 instructions at once, and by step 30 it's forgotten step 3. The ICM way: 👇 Break the prompt/workflow into steps. Each step gets a folder. The first folder is your first step. Then you point the AI at the first step, and the first step is 00-birthday-cake: (Point the AI just means giving access to the folders to the AI, through uploading or direct local access, don't worry about that now, let's keep building our cake.)