We have learned a few neat features of basic AI, now let's start learning how to interact with it! Two people, SAME free ChatGPT. One gets bland junk and says, "AI is overrated." The other saves an hour before lunch. They are both using the Same tool, no secret upgrade. The ONLY difference is how they are asking for it. Today you become the second person. 👇 The reframe I hold in my head for this is AI is not a search box and not a mind reader. It's an incredibly capable helper who does EXACTLY what YOU ask for, and AI cannot read your mind. So, the whole game is giving AI the same brief you would sending someone to the store. 🙍🏪The stage is set we are sending a neighbor to the store. 🛒 Just by asking our AI to "Get orange juice" makes the AI a talented guesser at what actually comes back. So, what you get is "3 gallons of Tropicana Orange Juice, Lots of Pulp, and a pitcher". The return is a best guess as to what you meant by "get orange juice, and you also got a pitcher to put it in which you did not ask for. Now, let's ask the same neighbor, but let's provide a better brief. Every AI request we send is a brief, and they work best when they are detailed instructions of exactly what we need. It's a specific errand, that will return great result. Example: "I need you to go to the store for me, I need you to pick up one gallon of Pulp-Free Tropicana Orange Juice, store brand is ok if they're out, but NO PULP is mandatory, if they have no pulp-free option, don't buy it, just come back and tell me, do not pick up anything else orange juice only." = exactly what you wanted. THE RECIPE (4 parts of a good brief) 1️⃣ Identity: Who it should be and what lens is it working with you from. "You are my friendly neighbor" 2️⃣ TASK: Exactly what to do, start with a verb. "I need you to go to the store for me" 3️⃣ CONTEXT: The details it needs, and the constraints. " I need you to go to the store for me, I need you to pick up one gallon of Pulp-Free Tropicana Orange Juice, store brand is ok if they're out, but NO PULP is mandatory, if they have no pulp-free option, don't buy it, just come back and tell me, do not pick up anything else."

Just thought I'd do a post in here after I was halfway through running six simultaneous Fable windows to try and max out the usage before it resets with a couple of in-depth security audits that I had planned... Then saw this update from anthropic around how in-plan Fable usage it will be extended until the 12th so I figured I'd post this in here to potentially save anybody from stressing over their usage if they hadn't seen an update from Anthropic. Read the full article below ;] Also feel free to share any thoughts below. I think it's great publicity but I'm definitely seeing some unhappy people who had altered their personal lives to try and fit fable usage into their routines. They are now unhappy about the late reminder, which I think is a bit crazy 🤣 https://support.claude.com/en/articles/15424964-claude-fable-5-promotional-access

I’ve been sharing in here about my work building a construction crew to help build bakeries - a workspace I have named Mira’s Forge. In my “hey I think I have 30-40 hours of Fable tokens left, YOLO!” post, @Alex Brown asked for a video about the build. And I was like “hmmm I didn’t film anything”, but in my next comment I was like “I keep *really* detailed records and I have Fable tokens which are about to expire” (or not, but I wouldn’t know that for about another 12 hours) 🤔. This is that video. Turns out it was long, because I talk too much and I keep detailed records. I’m hoping this might be of interest and value to some here. I would love to know what you think. https://youtu.be/vUSvUnlrcxk

It sounds pretty interesting and I am thinking of giving it a spin, but I am mostly interested in if anyone has used Jules: Googles asynchronous coding agent. It's the same price as Claude Code Pro Max plans $99.99 / month: 5x higher usage limits vs. AI Pro $199.99 / month: 20x higher usage limits vs. AI Pro Claims: Gemini Spark helps you navigate your digital life. Give it a task and it works in the background 24/7, even if your phone and laptop are turned off. It operates autonomously, but always under your direction. You choose to turn it on, and it's designed to check with you before taking major actions. Gemini Spark can connect natively with your favorite Google apps like Gmail, Calendar, Drive, Docs, Sheets, Slides, YouTube, and Google Maps. These connections are turned off by default, just head to your settings to turn them on. Once activated, Spark can help you take action across your entire digital workspace. Gemini Spark – Your 24/7 personal AI agent for productivity

This post is not about ICM, it's about learning the AI systems you are using in the ICM space. If you are new to ICM and you are looking to learn the structure and how to apply it, please see the posts below: (They will serve you well) 1️⃣Jakes Van Clief's Welcome: https://www.skool.com/cliefnotes/welcome-to-clief-notes-heres-where-to-start-2?p=f8f85a09 2️⃣Mira Bradsaw's collection of getting started: https://www.skool.com/cliefnotes/clief-notes-gems-for-starting-in-icm?p=0385cbf9 This is also not a post for people who have a handle on AI and are working in the space already, this is a post for the people who are sitting in the dark, trying to catch a moving train, and just need a clear view of the platform before they hope on. |---------------------------------Let's Begin---------------------------------------| 👇 Two opposite lies you've been sold: (1) AI can do anything, it's magic. (2) AI is coming for everything and will do it all better than you. Both are selling you something. Both are wrong. The truth is more useful. 👇 The picture that explains EVERY limit ⭐ When you are starting with AI, treat AI like a brilliant intern on their first day. 🧑‍💼👩‍💼 Sharp ✅, well-read ✅, lightning fast ✅, eager ✅. But your intern doesn't know your business, wasn't in the room yesterday for the meeting, has zero stake in the outcome, they will confidently do the wrong thing if YOU are vague, and they should NEVER send something to a client or make a final call without YOU checking. Let's hold that picture, it is one of the most accurate descriptions of AI you will see. (As you grow your knowledge some of this will change a bit, but don't worry about that now, it will come as you learn) What AI genuinely can't do - ⚠️ Truly understand (it predicts language, doesn't comprehend it) - ⚠️ Know recent events (AI has a knowledge cutoff date which is stale unless it can search the web) - ⚠️ Tell its own facts from its own inventions - ⚠️ Remember you by default (fixable, Post 13 🧠) - ⚠️ Have judgment, values, or accountability. It won't pay the price of being wrong. YOU will. - ⚠️ Know your customers, taste, and the 100 things you know that were never written down - ⚠️ Avoid hidden bias (it learned from human writing, so it absorbed human bias and can amplify it. - ⚠️ Nail exact math on its own (Many LLMs are actively trying to solve this known issue natively) - ⚠️ Take real actions by itself (I have never met an AI that has done something because it wanted too)