Join us on Zoom Saturday, July 11, 2026 12:30 ET - 13:30 ET we’re opening the AI for Life + AI Bits and Pieces session to everyone, including people outside the community. Join instructions https://us06web.zoom.us/meetings/81545596982/invitations?signature=NQBPitO7KYhO4f7NHMddMYVn476zmP8rjoEmkdhIvzY Meeting ID: 815 4559 6982 Passcode: 050131 Hosts: - 𝗠𝗶𝗰𝗵𝗮𝗲𝗹 𝗪𝗮𝗰𝗵𝘁 from 𝗔𝗜 𝗕𝗶𝘁𝘀 𝗮𝗻𝗱 𝗣𝗶𝗲𝗰𝗲𝘀 𝗰𝗼𝗺𝗺𝘂𝗻𝗶𝘁𝘆. - 𝗠𝗮𝘁𝘁𝗵𝗲𝘄 𝗦𝘂𝘁𝗵𝗲𝗿𝗹𝗮𝗻𝗱 from 𝗔𝗶 𝗳𝗼𝗿 𝗟𝗶𝗳𝗲 𝗰𝗼𝗺𝗺𝘂𝗻𝗶𝘁𝘆. This will be guided questions plus an open forum for practical discussion around what is happening in AI right now, including: - The explosion of AIOS aka Second Brain - AI hot topics and trends - Design and development - Workflows and automation - Process improvement - Tooling, use cases, and real-world implementation Join us for an open working conversation with people who have been building, testing, learning, and applying AI and automations in practical ways. 𝗦𝘂𝗯𝗺𝗶𝘁 𝗾𝘂𝗲𝘀𝘁𝗶𝗼𝗻𝘀 𝗽𝗿𝗶𝗼𝗿 𝘁𝗼 𝘁𝗵𝗲 𝗲𝘃𝗲𝗻𝘁 𝗳𝗼𝗿 𝗰𝗼𝗻𝘀𝗶𝗱𝗲𝗿𝗮𝘁𝗶𝗼𝗻. We’ll kick things off with pre-submitted questions. Simply submit your question(s) in the comments below, or direct message me in Skool. ✨ Claude will pick the question order. And of course bring questions, examples, workflows, problems, tools, or ideas you want to discuss during the open forum. Hope to see our friends there: @Ron Nedd @Frank Priboy @Gina Wang @Debbie Ai @Pedro Gomez @Usman Mohammed @Nick Mohler @Mike AI Consultant @Diane McCracken @R S @Collin Thomas @Jacob Brodsky @Bradley Kerman @Md. Abdullah Al Mafi @Michele Wacht @Mark Zayec @John Romano @Josh Frison

For those that were in the LIVE Session yesterday, I successfully downloaded Ollama onto my Windows laptop. For my non-technical members, Ollama is an LLM like ChatGPT that you run local on your computer - with no internet. It is what people use that are concerned about privacy and the frontier models using your information as training data. Claude Cowork was guiding me through the process, step by step. After a few diagnostic tests, the screen said: >>> Send a message (/? for help) I began what is effectively the local AI version of "Hello, world". Enter: “Summarize this in one sentence: The quick brown fox jumps over the lazy dog.” Ollama responded! Wow. Side note: It is wrong I am as excited as a kid in the candy store. My own AI model. Running locally. On my laptop. After a few more simple tests, Cowork suggested I verify that Ollama was truly working offline. The instructions were clear. ☑️ Turn off Wi-Fi. ☑️ Enter prompt. ☑️ Wait for response?!? Check. Check and Check! Holy Smokes! It actually works. Mind you, I am using Cowork to guide me through what feels like my first few steps on Mars. So... Now I decide to really test it with a complex prompt: "Can you write a brief story about two 12 year old boys throwing a football in the front yard, dreaming about playing in the NFL?" It produces a very nice short story. Offline. On my laptop. I am impressed. I am proud. Queue the tears... So naturally, I copy the story and paste it back into Claude Cowork to await my atta’ boy! Instead ⚠️⚠️⚠️⚠️ “We couldn’t connect to Claude. Please check your network connection and try again.” OMG! The F*&king WI-FI is off. LMAO! The local AI passed the offline test with flying colors. The AI helping me test the local AI did not. Now that is AI in Real Life.

Welcome to the Out of The Box Series — where I test how far curiosity and AI can take you in 30, 60, or 90 minutes, using today's best no-code and low-code tools. No setup. No training. Just pure exploration — right out of the box. 🎬 This Episode: Default Image Creation — ChatGPT vs Gemini vs Claude 🕒 Time Limit: One prompt, default settings 📂 Category: AI Image Creation OpenAI just upgraded its image engine, and I wanted to see if it lives up to the buzz. So I ran a quick test: - Same prompt, three tools - Default settings No tweaks, no custom instructions — just hit go and see what comes back. A few surprises along the way: 🔹 ChatGPT: The image came back clean and easy to understand, with great use of whitespace. The upgrade was instantly noticeable. This is my new favorite image creation LLM. 🔹 Claude: Surprisingly, Claude still can't create images natively. But it offered to connect to Canva instead. I'm a Canva subscriber and a big fan, so that was an easy "hell yeah" from me. 🔹 Gemini: The one with the stellar reputation for image creation — is the one that missed. Notice the landscape image has two Claude panels. ✅ My verdict, two words each: 🔹 ChatGPT: Professional, Balanced 🔹 Gemini: Incorrect, Colorful 🔹 Claude (via Canva): Pedestrian, Underwhelming The results are below. 👀 You be the judge. What do you think? Prompt Used: Pasted content below into dialogue box, selected "Image Creation" mode, and hit enter. Content provided to each LLM: The chart breakdown ChatGPT — Best for: creative content, coding, everyday workflows Strengths: multimodal, custom GPTs, long-term context recall Pro tip: automate workflows, build custom GPTs for writing/planning/analysis Grok — Best for: real-time trends, pop culture, candid takes Strengths: connected to X/Twitter in real time, sharp/punchy tone Pro tip: use for viral posts and social commentary with personality Gemini — Best for: Google Workspace integration, real-time data Strengths: deep Docs/Sheets/Slides integration, real-time search

"A picture is worth a thousand words." That phrase has always been true, but with today’s LLMs it is starting to take on a much more practical meaning. One of the quiet advances in AI is not just better writing, coding, or summarization. It is image recognition and, more importantly, image understanding. I have noticed this in my own workflow. In the past, when I wanted Claude or ChatGPT to understand what I was looking at on my screen, I would usually describe it first. I would explain the structure, the problem, or the context, and then I would paste the screenshot to support what I had already written. Now I often skip that step entirely. I just paste the image and go. And the AI gets it. That is a bigger shift than it sounds. The improvement is not simply that the model can read text inside an image. It is that it can often understand what the image is doing, why it matters, and how it connects to the broader conversation. In other words, the image itself has become usable context. I ran into this recently while organizing my directory structure for a new project. I needed to update Claude on changes I had made, and instead of describing the folder structure, I simply pasted the screenshot into the chat. Claude immediately responded: “That's a clean hierarchy: client → business area → project. Every future engagement follows the same pattern.” That response stood out to me because Claude did more than recognize folder names. It understood the hierarchy. It understood the logic behind the structure. It understood the intent of the organization. And it connected that image to the ongoing context of the conversation without me needing to explain much at all. This is starting to change how I work with LLMs, and I think it has broader implications for a lot of people using AI in practical ways. A screenshot is no longer just supporting material. In many cases, it is now the prompt. Example 1: A very useful example is organizational or workflow context, like the file folder case. Instead of describing a folder structure, a software layout, or a system you are building, you can often just show it. The AI can quickly interpret the structure, identify patterns, and give feedback on what is organized well, what may be unclear, and what the next step should be.

Fable comes back online today. We've all heard the name for weeks, so here's a quick guide on what it is and (more importantly) when to actually use it, so we don't waste money. First things first: What is Fable? (for anyone new to it). Let's imagine Anthropic's AIs like a "family of brains". The regulars are Opus, Sonnet and Haiku. Fable is the new, smartest one, the first of a new generation (the Mythos family), able to do things no other model could. Basically, it's the strongest Claude we can get. It disappeared for 3 weeks: - June 9: Fable launches, everyone's talking about it. - June 12: Amazon researchers find a trick that makes Fable point out software weaknesses (and once even write code to break in). The U.S. government blocks it, and since Anthropic can't check everyone's nationality fast enough, they switch it off for everybody. - Late June: they negotiate a deal with the government. - July 1 (today): Fable comes back on, worldwide. (By the way: other AIs like Opus 4.8, GPT-5.5 and China's Kimi K2.7 could all do the same thing that the Amazon researchers found. So it wasn't some unique "super weapon". Just a simple jailbreak that worked in other models, and those other models were powerful enough to point out those weaknesses too.) Now, the important part of this...WHEN do we use Fable instead of Opus? Is it really that powerful? Let's use an analogy. Think of a race. Opus is a great sprinter. Fable is a marathon runner that checks its own work as it goes. Fable's edge is long, hard jobs that run on their own. Anthropic's own words: "the longer and more complex the task, the larger Fable's lead." So the best option to use Fable is when the task: - takes hours or days, not minutes - has many steps and we don't want to babysit, supervise or check each one - needs to hold a LOT at once (a big codebase, a pile of documents... up to 1,000,000 tokens) - should check its own work and keep going until it's done - is genuinely hard (senior-level reasoning, a big migration, deep research)