Welcome to the group everyone, I got a bit of a shock this morning when I woke up to so many new member requests. So excited to have you all here @Eva Mandy @Riley Saint @Mabel Saade @David Wakeman @Enock Banock @Thomas Wintering

Know Your Color Energy 🌈 @Thomas Wintering did this for me and one for Suri. Mine basically broke down how I operate, and it was uncomfortably accurate. It broke my name into a pattern 💚 feel 🤎 ground 💙 speak 🟠 create 🤎 stabilise That’s exactly how I do things when I’m not messing with it. Every time I try to skip ahead and just “do”, it ends up messy. Because I haven’t actually processed it properly first. The birthday part was more the why behind it. Depth, intuition, all that. Which makes sense because I don’t do surface level anything. He did one for Suri too and that was ridiculously accurate. If you are curious about yours check out know your colour energy

Goose.ai Most people are still using AI like a chatbot Goose is different It’s an AI agent that actually does things on your computer What it actually is Open-source Runs locally Connects AI to real tools on your machine Not just answers Actions What it can do You tell it: “Build a small app” “Fix this bug” “Analyse my data” It: writes code edits files runs commands connects to tools like GitHub, Google Drive, databases Why this matters This is the shift: Chatbot → Agent less prompting less manual work more execution Real use cases build prototypes directly on your machine debug code without touching it query databases using plain language automate repetitive tasks What makes it different works with multiple AI models fully extensible with integrations runs locally, not just in the cloud Reality check It’s powerful But: requires setup not beginner-friendly you still need to guide it properly Goose = AI that executes, not just responds That’s where everything is heading next

Want to see how your year is actually going so far? Not the highlight version. The real one. Messy middle, half-built ideas, things that didn’t work, things starting to click. This is mine. PROMPT Create a highly detailed, visually symbolic image that represents how my year has been going so far, based on everything you know about my actions, goals, patterns, and progress. Analyse what I’ve been building, working on, and trying to achieve this year Include clear visual representations of my main focus areas (projects, business, learning, systems, etc.) Show the tension between progress and overwhelm, or clarity and confusion, if present Reflect how I actually operate, not an idealised version (for example juggling ideas, simplifying systems, starting and refining, etc.) Include small meaningful details that represent habits, tools, or repeated behaviours Capture momentum, even if it’s messy or inconsistent Scene direction: A single environment that tells the full story at a glance. It should feel like a snapshot of my real life trajectory this year, not a highlight reel Style instructions: Cinematic, ultra-detailed, strong lighting contrast (for example chaos vs calm, dark vs light), high resolution “Do not generalise. Base the image on actual behaviour patterns and priorities, even if it looks chaotic or unfinished.” Bobblehead version Create a highly detailed collectible bobblehead figure based on the uploaded image, packaged inside a clear display box. The bobblehead should have an oversized head and small body, with a recognisable likeness and a calm, focused expression. Slight head tilt or wobble for personality. The entire scene exists inside the box, like a premium figure display. Box design: Transparent front panel (like a Funko-style display box) Matte sides with subtle branding: “System Builder Edition” or “Messy Progress Series” Small printed labels on the box edges like: “In Progress”, “Under Construction”, “Do Not Simplify Yet” Slight wear on the box corners to reflect real use, not perfection

Turns out… it's not the model. It is how I am using it. Turns out Claude doesn’t count messages. It counts tokens. Once that clicked, everything changed. Here are 10 things that make a massive difference: 1. Edit your prompt instead of sending follow-ups If the response is off, don’t send: “No, I meant…” or “That’s not right…” Every extra message gets added to history. Claude re-reads ALL of it every time. Token cost grows fast: At ~500 tokens per exchange 5 messages = ~7.5K tokens 10 messages = ~27.5K tokens 20 messages = ~105K tokens 30 messages = ~232K tokens Instead: edit your original prompt and regenerate. You replace the history instead of stacking it. 2. Start a new chat every 15 to 20 messages Long chats are expensive. Most tokens get burned re-reading old context, not generating new output. One dev tracked usage: 98.5% tokens = re-reading history 1.5% = actual output Fix: Ask Claude to summarise → copy → start fresh chat → paste summary. 3. Batch your questions Stop sending multiple messages. Bad: “Summarise this” “Now list points” “Now give a headline” Better: “Summarise this, list key points, and suggest a headline.” One prompt = one context load. 4. Use Projects for repeat files Uploading the same file repeatedly = repeated token cost. Projects cache your files. Upload once → reuse without re-tokenising. If you use PDFs, briefs, or docs often, this alone saves a lot. 5. Set Memory and Preferences If you keep typing: “Act as…” “I’m a…” “I write like…” You’re wasting tokens every time. Save it once in settings. Claude remembers it. 6. Turn off unused features Search, connectors, advanced thinking all add token cost. If you didn’t intentionally turn it on, turn it off. 7. Use the right model Not everything needs power. Haiku → quick, cheap tasks Sonnet → standard work Opus → deep thinking Most people overuse powerful models and burn budget fast. 8. Spread usage across the day Claude uses a rolling 5-hour window. If you burn everything in one session, you waste the rest of your day.