Self proclaimed, junior, non technical, back end vibe coder here 🤣. Looking for a little guidance or a point in the right direction for presentations, images, videos, webdesign etc. Sorry for the long post. Some context and then 4 questions. Im working my way through the lessons in the Premium section during lunch breaks, evenings, weekend, 2 kids and a 34week pregnant wife, all around the day job. I wanted to see if someone more experienced than myself might be able to help me streamline some learning. 1. Long form source/research management 2. Presentation/pitch creation 3. Video creation 4. Website creation This is not a request for instruction and a how too. Im looking for support with direction, potentially revealing any unknown unknowns. Im more than happy to learn myself, in fact I prefer it. There's lots of content creators sharing super simple, very impressive workflows and skills but I want to keep things super simple and ICM workspace first if at all possible. Im a fast, practical learner who is time poor so im just looking for some help to avoid wasting time while achieving the most impactful results. I dont mind sinking the hours. As you will hopefully appreciate though, due to my personal circumstances, they are very expensive right now. 1. Im accruing a alot of long form, well cited, deep research reports, transcripts and other wordy source docs. These are all housed in my workspace. Is this fine and best ICM practice as long as separation of concerns is properly adhered to or is there a more productive approach to library sources? 2. Ive two big presentations I need to prepare by 20th and 23th July. I've yet to pick up the presentation lesson in Premium. Ive got the sources, the material, I just need to pull it together and ive decided this will be the first time I'll not be doing it manually. I've seen the presentation lesson in the Premium section, Jeff Su's Notebook LM video and a coyole of others. Ive yet to put any of it into practice and feeling a little overwhelmed on where to go to get the end result. Does anyone have any advice or direction on where to direct my learning efforts?

There are rumors of Opus 5 landing sometime after the 20th, and talk of a Mythos 6 sitting behind it. Everyone is about to be asking the same two things: do I upgrade, and do I switch. Before that though, the thing I keep coming back to is that the model matters less than how you prompt it. And I have actually been moving down in power, not up. Here is what changed how I prompt. The biggest lever is not the size of your prompt. It is the effort level you let the model run at. The mistake I was making was cramming the prompt with decisions and instructions. Every decision you make for it up front is one it does not get to make, and it quietly caps how high the model can reason. I came across a study recently making the same point: you want to let the model make as many of the decisions as it can, rather than pre-making them in the prompt for it. So the move is to front-load the context and the guardrails, not the decisions. Give it the full picture and the rails it has to stay inside, set the effort level high, and then let it search, orient, and decide for itself. Both extremes fail. Too little context and it is flying blind. Too many pre-made decisions and you have capped its ceiling before it has started. The skill is handing it the material and the boundaries, not the answers. This is what pushed me toward lower-power models for most of what I do. When the context is set up right and the effort is turned up, a smaller model handles the vast majority of the work. The only times I actually reach for a frontier model now are the high-stakes ones: folder restructuring at scale, a large migration where a lot is on the line, or really in-depth analysis that has to weigh qualitative inputs as well. So for me the Opus 5 question is not "will it be better." It will be. It is "how much of my actual work genuinely needs it." What's your current daily driver model and why? Do you see Opus 5 potentially taking that spot?