Hi, I was looking to connect with someone who can offer insight into supply chain processes. I want to know whether you think ICM fits into these processes as well as the ‘why’ behind it. I’m looking to establish a niche, and helping supply chains seems like an interest area to explore, but I have no experience at all in supply chains, so I’d like to gather some insider info :)

I realized that my background in Psychology is especially useful in understanding learning patterns in humans. So I thought: what if I apply it to AI? Unfortunately, AI does not perceive anything as a reward, but here are some interesting perspectives gained from my conversation with Claude on creating/improving a self-learning loop: - Encoding specificity. A lesson works best when it's loaded where the cue occurs. A global lessons file competes with everything else in context. The same rule placed in the CONTEXT.md for the task it governs gets applied far more consistently. - Implementation intentions. "When drafting outreach emails, cut the first paragraph" beats "I prefer directness." If-then phrasing gives me a trigger, not a vague value I have to interpret. - Contrastive examples. One short good/bad pair often transfers better than a paragraph of explanation. It shows where the line actually is. - Interference. As lessons accumulate, they start blurring and contradicting each other. Your proposals inbox needs a consolidation step: periodically merge, prune, and resolve conflicts, so you keep 10 sharp rules rather than 60 overlapping ones. - Salience. Rules buried in the middle of long files get underweighted. Put the few that really matter near the top.

My son was born this week, Azrael is his name. Creation is a wild thing, I decided to spend some time (the little time I have) writing with just my own two hands as a celebration of the human life. No ai used in the script or writing, I hope y'all enjoy it. If you do please like and share and comment on YouTube.

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.

It started with prompt engineering & make.com/n8n; I thought that was it. Then came ICM, and after a month, I thought I had it figured out. A few months in, I am more confused than ever before. I realised that there are no rules; there are just different ways of working, and you can be inspired by them. Although committing to one way of doing things might get you consistent results, you'll never know what might come from doing it differently. I have been reading The Pragmatic Programmer (a great book for, but not limited to, understanding the mechanisms behind what makes ICM such a great method), and I have been going through The Wise Architects by @Bas Rosario and man... Doors just keep opening, but as these doors open, the maze keeps expanding🤣. Currently, I'm dealing with understanding when to be specific vs when to be less specific to AI (so as not to restrict it too much). Writing instructions that are too specific would limit the model’s capabilities and leave you spending too much time on a workflow you’ll eventually need to adjust because it's too restrictive. What are you struggling with now, and what do you think is the solution to your struggle & why?