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?

A little humor to start your week! I found this way too relatable, mirroring how I feel sometimes when I try to talk about AI with people I meet or know who don't use the tools and can't see beyond the negative narratives. I don't judge it, it's biology, and a repeated pattern that comes with every big tech shift or invention. They'll get there in their own time. Grateful for finding my fellows Straxs though! Have a great week everyone! (S7E6 - The Snowmen)