### Make money doing the work you believe in Start your SubstackLearn more I can’t believe tomorrow is my first Father’s Day! --- The Tom Ford Gucci dress (FW 1999) does not cancel out the Meta glasses, but nice try! Cait Conley, the candidate the TPUSA teenage tradwives tried to drag for “looking like Dylan Mulvaney” (like thats a bad thing) - has won her Primary and will hopefully unseat Trump loyalist Rep Mike Lawler in November. Cait is a **Decorated Combat Veteran and National Security Expert,** she is the **first women in Special Ops leadership**, and… You always own your intellectual property, mailing list, and subscriber payments. With full editorial control and no gatekeepers, you can do the work you most believe in. Start your SubstackLearn more I’ve been Balenciaga-ed in Cannes. Love the bolero bag with the pink tailed heavy silk crepe tee. [go.shopmy.us/p-66850934](https://go.shopmy.us/p-66850934) Put two people in a room and prompt them specifically to never start up a conversation, and see how long they hold out. As “true” agents, are we free to not think our next thoughts? Great read, but there definitely seems to be some unexamined philosophical assumptions here. AI is never the subject. At the very core, there is no spark of agency. It’s inescapably a reactive thing. It simply can’t “do” anything unless it is first prompted to do so. Nerds thrill when chatbots engage in a “conversation” with each other; but put two chatbots in a virtual room and never prompt either, and neither will ever start up a conversation. There is no unmoved mover. It’s a rabbit-hole and I needed to keep the piece readable in both length and form. Tell me what I’ve missed, always happy to dive in deeper in a future installment…! I can appreciate the constraints, but It’s a rabbit hole because it’s genuinely philosophically fraught, so there’s lots of debate. For instance, you take a stance on the free will debate without acknowledging it by claiming that, contra AI, humans are (or have within them) an “unmoved mover.” That was my point about putting two _people_ in a room and instructing them to _not_ have a conversation. At some point, they’d break and start talking, not because they’re free to do so, but because they’re _…_ Claude Code can now write its own workflow and run hundreds of agents in parallel. I just broke down how `dynamic workflows` work, and what they actually cost, in part 1 of my agentic engineering series. I’m constantly updating these posts over time, the piece has also grown sections on prompt caching and context rot. Worth a read if the series is new to you, or if it’s been a while since you read it. Agentic Engineering, part 1: The Configuration Layer Does anyone seriously think we stumbled into building conscious machines, just because we trained them on human language? Help me understand here. 7 hours on an article. 2 likes. One was my mum. 20 minutes on "AI lied to me." 1000 likes.