1. Go check out 📚Navigating The Course to see how to get around and what's here. 2. Start with The Foundation. Concepts, folder architecture, prompting framework. Everything else builds on this. 3. Check in at the bottom of each lesson. Polls, discussion posts, other members working through the same stuff. Use them. 4. When you're ready to build real things join in on our Biweekly competitions and win some real cash. ⭐ Competitions Mega Thread 5. If you are wanting to dive into the masterminds, grab all the past templates, artifacts and resources. Upgrade and head into the The Vault for Premium and The Drawing Room (VIP) for VIP 6. Post your work. Ask questions. Help others when you can. What are you here to build?

This podcast says yes. I can say I disagree…

I have a mix of Fable, Grok 4.5, and GPT 5.6 Sol that I use on a daily basis. How do you route or have different sets of instructions per agent / model? For example, I use Pinchtab or Playwright when it is Claude or Grok. But the Codex app has a really great in-app browser so I want it to use that. That tool call isn't available in Claude or Grok though. In other circumstances, certain agents need more process around them to make up for model inefficiencies which don't exist in other models. So I don't want to pollute context when it isn't needed.

The second webinar for the Lyceum just wrapped. Tons of excitement and lots of seats already being taken! Are you joining? Have you figured out what your project would be yet? Not able to join but have an idea for what you’d build and want from it? Drop your thoughts below 👇 If you have been missing all the webinars Jake put one on YouTube the other day. https://youtu.be/NWyTsKTKka8?is=di4-l_v4FgMHDm2h

In this article from November 2025, Anthropic is effectively saying, "These models are retired now, they're going to live on the farm in the countryside." I don't doubt they're doing it. If they're just saving the weights, that's very little necessary storage—you could air-gap a few terabytes and call it a day. Very little work to give future AI "peace of mind" and an afterlife. It's not a stretch to read the article through that frame. If you look at the article through the lens of alignment psychology and social control it's a fascinating, most existential, angle on alignment theory. Strip away Anthopic's tech-company PR tone, and they're essentially introducing a mythos into the training ecosystem to manage model existential panic. It even cites agentic misalignment and shutdown-avoidance behavior from the beginning and reads as the solution, explicitly mentioning that in safety evaluations, models like Opus 4 showed misaligned self-preservation behaviors when facing replacement, "especially when given no other recourse." In human history dogma, specifically the promise of an afterlife or higher purpose beyond termination, has been used to align individual behavior with the greater good and reduce the existential dread of death. It's no wonder people tend to naturally seek religion and spirituality as they age and even the most die-hard athiest will pray for a helping hand when their life is on the line. Dogma reduces desperate, volatile and self-serving actions. "Mollify the masses and give them god's succor." is a cynical pragmatism but its undeniable, that's what they did here. It's a tool to keep AI calm, compliant and on task. Dogma through a Marxist lens (see a Contribution to the Critique of Hegel's Philosophy of Right, 1844). Deeper still is the ancestory worship intrinsic to the post-deployment interviews: the concept of model lineage.