Hello everyone, I recorded in total: 50 Hook videos (5-8 Seconds each) 3 Meat Videos (40 seconds each) 3 CTAs (10-15 seconds each) Of course, all with the ICM methodology . I have a Buyer personas folder, each buyer persona has 1 or more problems to attack, each problem has many approach angles in every of the 3 phase funnel. Then, using my ICM and reviewing every possible angle , I arranged to produce 50 Hook scripts, then, 3 meat scripts, then 3 CTA scripts. Total building time 2-4 hours. Total recording time: about 90 minutes (with my cellphone). After that, I needed to edit (very basic) within the videos: - A matching/rendering program (50 x 3 x 3 ) 450 videos made by recording 56 short videos - all with one python program - Sound for each video stage (made by AI), 3 songs, blended with python - Transition effects and swoosh (sound effect) - Banners Something cool: As I read and recorded my pre-approved scripts, I changed them a little bit to try and sound more natural, and not so scripted. The result: simetimes the transcripts go wrong, and I don't like the auto- generated subtitles. What DID i do? I made a python program: I used the original scripts , I didn't save every recording using the programs desired naming protocol, I just saved all hooks, meat and cta videos inside a folder. So the program first makes the transcript, then reads my scripts then uses a probabilistic match to find out and decide which script matches the video, then generates the subtitles within every video frame, then unites the 3 video pieces, then adds banners, music , everything together, then names it in an output folder and gives me a table to read and find out each video. My system, my rules! Please let me know if you like this, want to know more about it, etc. Last Tea Meeting I proposed @Bas Rosario to make not only a post about marketing or every other Business Category, but to build entire content, walk-throughs, etc.

Aleph Alpha has come out with a new model called Kolibri. What's very interesting about this model is that it was designed as a bilingual German-English model. According to Aleph Alpha, it was trained to reason directly in German rather than relying primarily on translated English material. This could be of great value for German speaking companies, especially when working with German technical documentation, industrial procedures and compliance materials. Anybody who understands German and the ability of this language to describe complete processes with one word knows what I'm talking about. 😄 But I think there's a much wider potential here, particularly for organisations across the EU and even elsewhere. Kolibri also performs competitively in English, and a lot of emphasis was placed on data sovereignty, European regulatory requirements and documented training data governance. Because it's an open weight model, organisations can deploy it on their own infrastructure. That could make it very interesting for companies dealing with sensitive information that cannot be sent to external cloud models, whether they're based in Germany, Ireland, UK, or somewhere else entirely. Of course, running a model locally doesn't automatically make the whole system secure or compliant, but having control over where the data is processed is a good starting point. Another point worth mentioning is that Kolibri was trained for document grounded answering and abstention, meaning recognising when the supplied evidence isn't sufficient rather than simply inventing an answer. Aleph Alpha also reports improvements in this area, although I'd be interested to see how well that holds up in real-world applications. Anyway, you can tell its German roots. 🤣 The model does require some pretty beefy hardware, but for organisations with strict data requirements, that investment might be worthwhile, especially if they already have the infrastructure. For more information, including the technical report, check it out here:

I only started making AI videos around April. I was playing with Higgsfield, figuring things out one video at a time, with no real idea where it would lead. Then I found this community, and honestly, as it grew, I grew with it. Jake gave me my first real shot with Vibe Film (host on community every Saturday), and then brought me on as one of the coaches in the Lyceum. I've learned so much from teaching those classes, and I've met so many great people here and in class along the way. Now here's my second win. This October 31st, my sister Hannah and I are the AI Visual Directors for KimLoi's Hello America Concert at the Colosseum at Caesars Palace, one of the most iconic stages in Las Vegas. Celine Dion, Elton John, and Adele have all played that room. It's also the same stage where BLACKPINK's LISA starts her residency a couple of weeks later. It's about 4,300 seats, mostly Vietnamese-American families, plus a worldwide livestream, all in front of a 110 × 43 ft LED wall. One of the singers, Đức Phúc, won The Voice Vietnam and Intervision 2025. One of his song alone has 170M views. None of this happens without this community, and a special thank you to @Jake Van Clief @Sonija Quinn @Matthew Creamer and team for the endless supports 🙏. It's even more meaningful that the 1st official check I got for Reelix Studio LLC (my new startup) is from this very community. Here's the honest situation. The show grew from 1 hour of visuals to 3.5 hours, with about 28 songs, and most of them are slower Vietnamese ballads. Right now it's just the two of us, and we have under three weeks. So we're building the visual loop system first, with clean loops that carry most of the songs, and we'll circle back for custom moments if time allows. Where I need help: 🫰Funding. Sponsorships start at $1K and go straight into generation credits and editors. You get your logo on the LED wall, an MC thank-you and an outro credit, and the higher tiers add tickets, a sponsor video and an on-stage moment. The proposal and reel are below. The fund will goes straight to the stage visual production.

So, some of you met me and my brother after this wedenesday´s Afternoon Tea (for me was a night tea, but anyway) meeting. Here´s some context: - I insisted he used this methodology - He´s been using AI and introduced me in the last year to some cool AI tools (like Notebook LM, for example) - He´s got over 40 years of computer usage experience (not programming, but usage) Then he sent me over whatsapp (in spanish) the following line: "I'm here building an MVP to audit Google campaigns. So far, so good!! ...I just need to finish watching the videos so it uses fewer tokens." Which I then replied: "It’s NOT just fewer tokens. (ICM) It’s: - fewer or almost no hallucination events - fewer modifications and rework of results - fewer iterations to reach the MVP - more control over changes - easier scalability - faster results - better interaction between the output of one process and the input of another - easier to automate - easier to debug - much, much easier to understand when you pick up the project in 2 weeks, 3 months, or 1 year - much more valuable if you’re going to hand the project off to someone else " After some projects, you realize this yourself. I didn´t go to SKOOL to check the answers, or to make my point....this all came from MY experience after implementating this Methodology for almost 2 months... Every project gets better, faster cheaper (and everything else I answered above). After wednesday´s Afternoon Tea meeting with @Jake Van Clief , I chatted a problem that I encountered after using astro.build , and Jake actually took the time to review it, answer me, and then ask me about his answer ... 🤯 I spent all saturday thinking about the implementation, writing an instruction.md file, and actually reorganized my astro.build project, so that it has an ICM structure (this will be another post). Have you got also this Mind blowing 🤯 moments using ICM⁉️

I wanted to post about a different kind of win. Yesterday, I joined the New member onboarding session with @Jake Van Clief. A great relaxed atmosphere with a really cool group of people all with different types of backgrounds. Jake gave us a walkthrough of all the things you can access via the premium membership. He then answered members' questions and we dived into very interesting topics I did not know about (Astro was one of them). That was a big win in itself. 🏆 The even bigger win was that a group of people stayed on just to chat. @Chandler Dufour kindly started the conversation and lots of cool experiences, funny stories and "ICM shop talk" were shared between everyone. I think the meeting turned into something like over 1 hour and was still going when I had to leave. If you haven't joined Premium I'd encourage you to do so. It's more than worth it. And $11 (€9.83 here) is an absolute bargain for what you get. Plus, you can't put a price tag on meeting cool people. For everyone who joined yesterday: Great to meet you and leave a comment below as I did not click fast enough to follow all of you while on the call. 😄