Some context: I was chatting with fable, asking about pros and cons of planning for code sessions using chat mode vs plan mode in Claude code. I worked out an entire plan and asked fable to generate the plan based on how Sonnet 5 operates, so it can do its job as best as possible. Reading and iterating over the entire plan, I noticed that fable wrote prompts that included quite a lot of steps per prompt. This surprised me and it made me chat in other chats using fable 5 as well as opus 4.8 (to reduce bias), and they all came to the same conclusion on how to best deal with Sonnet 5. It made me realize that the methodology of following a step by step prompting plan in Claude code may be outdated now that we have Sonnet 5 and I’m starting to think that it may be more worthwhile to work out a detailed plan using chat mode and give that plan in its entirety and the associated commands in larger chunks to Sonnet 5 for execution. Maybe this will save lots of tokens! What do you think? How do you use Sonnet 5?

There's something happening in here that I feel like I need to surface. I just cut a short from our conversation with Brian Clark on Bullhorns & Bullseyes. If you don't know Brian, he's the founder of Copyblogger—started it as a one-man site in 2006, before "content marketing" was even a phrase, and it's been called one of the most influential blogs in the world. He didn't invent blogging, but he's about as close as anyone to inventing what blogging became for business. Near the end of the episode, he says... "We're tribal. We can't shake our evolutionary upbringing, where you are attracted to people like you. That used to be based on appearance or geography, and now it's identity. And what is identity? It's a bundle of beliefs." He'd just said belonging is going to be more coveted, not less, as AI floods everything with things we can't tell are real. And the belonging that's left standing isn't geographic. It's not "we live near each other" or "we look alike." It's "we believe the same things." Now, for those of us in this community, we didn't all show up already agreeing on everything, and we didn't converge here because Jake is the guy to follow. We converged because @Jake Van Clief said something true first, and a few thousand of us recognized our own belief in it before we had words for it ourselves. That's how this works—someone has to say it first, most of us here, especially in the beginning, didn't need to be convinced. We were being reminded. This concept isn't new. It takes the same shape as every real reformation does. Belief stops living inside one person or institution and starts living in whoever recognizes it. Jake didn't build a following. He built a mirror, and we all walked up and saw ourselves in it. @Ruben Aguirre already did this in here—put his actual beliefs on the table, not a bio. If you're willing, I'd like to hear yours, too. But I'll go further than that. You've already been doing the belief work if you've built an ICM.