In our Vibe Film session we took a viral reel, broke it down live, and built our own version from scratch with AI: a scooter, a pig, a car and a plane that are all flat painted cardboard. I turned the whole thing into a 7-minute how-to so you can follow every step: - breaking down the original into a recipe - three ideas as 3x3 storyboards before spending a single credit on video - character, location, palette and prop sheets - frames to clips, starting every shot one beat before the action - the mistakes ICM is what kept it together: one folder, one set of notes, every prompt and asset saved as we went, so nothing got lost between steps. The one rule from this session: give every prop its own sheet, and start every shot one beat before the action. ▶ Watch it here: https://youtu.be/IFYOROMBOBI 🎨 Every prompt, sheet and clip is free on Higgsfield. Hand them to your own AI and make your own version: https://higgsfield.ai/@danneytee/projects/cant-afford-it-paint-it (More remakes like this in our room: https://higgsfield.ai/community/rooms/viral-remakes) Thank you to everyone who came to the session for the questions and the kind words. If it's useful, a like and a subscribe would mean a lot. It helps me keep making these. See you at the next Vibe Film session. — Danney

Same wall, every time. I ask a model for docs and I get one blob that serves nobody. Too fuzzy for an agent to follow without drifting. Too stiff for a person to read without squinting. And when I ask for a diagram or a video on top, the wrong claims just get prettier. So I built doc-clarity. One topic in. Writing you can check. Then a climb, one rung at a time, as far as the brief asks: text → diagram → web page → explainer video. https://github.com/dvogeldev/doc-clarity Rung 1: the writing. Three separate files, each under a real standard, because an agent and a person should never share one mixed document. 1. machine/text.md, full ASD-STE100. Controlled vocabulary, one meaning per word, short sentences, active voice. This is the file your agent or your code reads. It's deterministic, no "did the model mean this or that", and a checker script (ste_check.py) audits it. It writes pass or fail. Fail means the agent fixes the text and runs it again. 2. ste-human/text.md, STE at 80%, only when you ask. Most of the discipline, but a person can actually read it. Technical precision with humans in the loop. 3. human/text.md, ISO 24495-1 plain language. Four principles: relevant, findable, understandable, usable. The test: after one read, the reader can do the thing. Rung 2: the diagram. A hard paragraph becomes a figure. One claim per figure, and no new claims. The figure shows exactly what the writing already says, nothing more. You get an editable source file, not a baked PNG you can't fix. Rung 3: the web page. One self-contained HTML file. Interaction only when it helps the reader do the task. It's discardable, cheap enough to make for one topic and throw away. Rung 4: the explainer video. The narration and the shot list get written first, and they're checked against the writing before anything renders. Claims match, order matches, then render. No API keys stored. Why the order is fixed: 📐 A wrong claim is cheap to fix in text and expensive inside a video. Every later rung repeats the checked claims. It never extends them.

Something I’ve been trying to wrap my head around is Jake’s Edubaware. Like most learning exercises, I start with a Google NotebookLM of the top sources on the topic. This time I had it build a slide deck overviewing Edubaware, then exported the whole thing as a PDF. Attached. The short version: it’s multiplayer folders. You take an ICM (a folder of files that already tells the model exactly what to do), freeze it as a template, and launch a workbench. Everyone on the team works against that same shared copy. The agent knows who is typing. No more hunting through separate chats for the good version. It’s basically the same shape as opening a project folder and running a few AI sessions against it—except the folder is shared, the template stays frozen unless a builder updates it, and you control the org, the roles, and the keys. Upload the zip that already works on your machine. It works for everyone you invite. Thought I should share the deck. Let me know what jumps out.

Hey everyone! I'm honestly so excited right now, and a little emotional too. With the recent changes at Eduba, I can feel a lot of new doors opening for me. For the first time it feels real that I'm one step closer to leaving my day job and spending my days doing what I love. I've been chasing this for a long time, so I wanted to give back the best way I know how: by making something and sharing every bit of my knowledge back to the community. What has me SO pumped isn't even the dragon. It's that I'm finally getting my work "mapped out": 1. Every project has one file that says where things stand and what's next, so I (or the AI) can pick up right where I left off. 2. Before anything moves, my face, the dragon and every place get locked as reference sheets, and every shot points back to them. 3. Prompts follow the same template every time: the lens, the action timed in seconds, what must not change. 4. The edit itself is a script, so when I give a note like "the music is too loud" or "this shot looks off," it gets fixed and the whole video rebuilds. 5. Every note I give becomes a rule, so I don't have to give it twice. I really can't take credit for the thinking behind it. I learned it from being part of the Lyceum and watching how Jake thinks about folders and context: write everything down so anyone, person or agent, can walk in and know what to do. I'm still learning from it every single week, and I'm grateful to get to be around people who think this way. This is my small way of giving something back. I'm going to keep putting real time and effort into videos like this, and keep showing everything, mistakes included, so you can take whatever's useful and run with it. Here's the full video if you want to see it: https://youtu.be/3Cq2kKzbn_s Full prompt: https://higgsfield.ai/@danneytee/projects/@id__8969e90e-c11b-483b-beda-8c0226994f8f?from=%2Fcommunity%2Frooms%2Fviral-remakes%3Fscope%3Dmine

Over the past couple of days, there have been numerous discussions about the heavy use of acronyms in the AI space and the overwhelming frustration that those new to AI often feel when trying to understand conversations in the community. I created this resource to help.Below is a comprehensive, well-organized list of the most commonly used acronyms in AI — covering LLMs, prompting techniques, model architectures, training methods, tools, and more. Whether you're just starting out or looking to fill in the gaps, this should serve as a quick and handy reference.Commonly Used Acronyms in the AI Space Core AI & ML Foundations - AI — Artificial Intelligence - AGI — Artificial General Intelligence - ASI — Artificial Superintelligence - ML — Machine Learning - DL — Deep Learning - RL — Reinforcement Learning Models & Architectures - LLM — Large Language Model - SLM — Small Language Model - LMM — Large Multimodal Model - VLM — Vision-Language Model - GPT — Generative Pre-trained Transformer - BERT — Bidirectional Encoder Representations from Transformers - MoE — Mixture of Experts - CNN — Convolutional Neural Network - RNN — Recurrent Neural Network - LSTM — Long Short-Term Memory - GAN — Generative Adversarial Network Techniques, Prompting & Alignment - CoT — Chain of Thought - ToT — Tree of Thoughts - RAG — Retrieval-Augmented Generation - RLHF — Reinforcement Learning from Human Feedback - DPO — Direct Preference Optimization - LoRA — Low-Rank Adaptation - QLoRA — Quantized Low-Rank Adaptation - PEFT — Parameter-Efficient Fine-Tuning - ReAct — Reason + Act Other Practical & Business Terms - POC — Proof of Concept - MVP — Minimum Viable Product - GenAI — Generative AI - MLOps — Machine Learning Operations - AEO — Answer Engine Optimization This list focuses on the acronyms you’ll encounter most frequently in papers, forums, product documentation, and day-to-day AI discussions. Feel free to bookmark this post — I’ll keep it updated as new terms become common. If you come across an acronym that’s missing or want a deeper explanation on any of them, just drop a comment and I’ll add it.