Opus 5.5, Sol 6, fable 5.1, Astra 6. Models are being released now faster than anyone can keep up. The online dialogue gets all excited every few weeks when a new one is announced, but the reality is we’re several generations deep into models that can already reliably do almost anything you can think of. The beauty of ICM is that you aren’t tied to any model but I’m wondering how folks are navigating having so many options at their fingertips. I’ve started letting my sessions decide what to use as I can’t keep up anymore. How are you choosing what to use? Leave a comment below 👇

When I first started my entrepreneurship 15 years ago, the very first book I read was Dan Kennedy's "The Ultimate Sales Letter". It really set me down a direct sales marketing path that led to my first "6 figure" business in 90 days. I did it on the back of direct mail. (I got free Fedex envelopes and wrote a P.A.S. letter to 3 people in the same niche and said I can only help one of them, whomever calls first, and my phone blew up). The most important element in a sales letter is the headline. This is true today, more so than ever. Your pages success starts and ends with your headline. You have to hook them in. This post's title is an example of a hook, opening a loop, and the end of this post is the example of closing the loop. If you run ads on line, or create video content...it's the same thing. You have to hook them in, so all of my videos , I try to have a "hook" in the front, so that people stay and don't bounce immediately. I've been a hooker for well over a decade. After joining this group, I realized there was a different kind of "hook" I needed to learn. That's the hooks built into Claude Code so that it follows my rules. So, if you ask me...there's nothing wrong with being a hooker. Because I am one and I suggest you be one, too. Questions?👇 P.S. I forgot what I had named my skill but you will see by how I named it that I had to figure out hooks for my own sanity. I show the terminal while in the production for this video and you see the hooks that fire.

Look what ChatGPT says after reading the Terms of Service of JEV .. 😬 what do you think? TYPE SAFE CONTRACT REVIEW — MAIN RED FLAGS If this service will handle confidential, regulated, or customer-facing data, I would not sign these terms unchanged. • DATA DELETION TypeSafe can delete Customer Data at any time. The agreement provides no guaranteed export window, transition period, or deletion schedule, and allows retention in backups. Ask for a defined export period, deletion timeline, and backup-purge process. • BROAD TELEMETRY RIGHTS TypeSafe may use Customer Data indefinitely to create “Telemetry,” including hashes, classifications, metrics, and “learnings.” It may then use Telemetry without restriction to improve other products. Ask that Telemetry be aggregated, deidentified, and non-reidentifiable. • VERY LOW LIABILITY CAP Liability is capped at the greater of 12 months’ fees or $50. Lost data, security failures, and consequential damages are excluded. That is especially unfavorable for production use or sensitive data. • BROAD CUSTOMER INDEMNITY The customer indemnifies TypeSafe for claims involving Input, the customer’s application, license violations, and essentially any End User claim related to the service. This should be narrowed, made mutual, and limited to third-party claims caused by the indemnifying party’s breach or negligence. • NO CLEAR PROTECTION FOR AI OUTPUT TypeSafe assigns Output to the customer but excludes Output from its IP indemnity. The customer may therefore bear much of the risk that generated output infringes someone else’s rights. • WEAK SERVICE COMMITMENTS There is no meaningful uptime SLA, support-response commitment, recovery objective, or strong remedy for outages. TypeSafe may also change the API in ways that make the customer’s application incompatible. • CREDIT AND PRICING RISK Credits can expire, are nonrefundable, and may be consumed at changing rates. Automatic refills can also create additional charges. Ask for spending limits, advance notice of rate changes, and no automatic refills without separate approval.

@Ry Mac posted about helping his dad write a book: record him talking about his life, let Claude turn the transcript into chapters. Good post. Good instinct. I used the same method (with ChatGPT two years ago and published a book on a Yoga Style called BikYasa Yoga https://www.amazon.com/dp/B0D4QTCLZH?lv=shuf&channelId=500&plpRedirect=mhFallback). I read it Ry Mac's post twice, and the second read wasn't recognition. It was closer to déjà vu. I didn't set out to build a team of AI workers. I set out to finish a book that had been stuck for longer than I want to admit — one of several, all half-written, all going nowhere on their own. The actual method came from @Jake Van Clief: one worker, one job. Not one assistant asked to do everything passably. A separate one, built for exactly one thing. So the first two were small and specific: a transcriber that turns spoken audio into clean text, nothing else, and a content editor that takes that text and shapes it into something a chapter can be built from. The reason those two existed was a technique from a writing workshop: answer the book's questions out loud instead of staring at a blank page and typing them. Dictate the answer, the transcriber converts it, the editor refines it into prose. Two workers, one job each, built for that loop and nothing more. The book got finished. Then it needed a cover, so I built a designer. Then it needed somewhere to live, so I built a builder. Then it needed people to actually find it, so I built someone for marketing. None of that was planned before the step before it went stuck. Each one showed up because the real work hit a wall without it — never because a diagram said it should exist yet. Five books came out of that, in forty-five days, before any of it had a name worth putting on a page. The post this morning is describing a discovery.

The other day I was driving home from work, turning over a question I keep circling: what's the best way to teach ICM, or to learn it? Almost immediately it clicked. Make it a game. So I pulled out my phone, opened the Claude app, and we went back and forth until the concept held together. I wrote it up as a PRD, and the minute I got home I handed it to Claude Code. What came out is a little game to teach ICM, the methodology we owe to Jake van Clief: an agent only knows what's on its path. Get the structure right and it does great work on its own. Get it wrong and it fails, cheerfully. Meet Bip. Bip is a robot intern at a painting shop, and Bip is not stupid, just literal. It reads exactly what's in front of it and does exactly what the signs say. Your job isn't to fix Bip. It's to fix the folders Bip has to walk. Move the right file onto its path. Drop a signpost in the room where the work actually happens. Send a helper into the messy folder so Bip doesn't drown in it. Wall off the stages so yesterday's notes don't leak into today's invoice. Thirteen levels, about fifteen minutes. Each one breaks in a different way, and every break is a real ICM lesson you'll feel before anyone explains it. Watch the battery drain and the little brain jar fog up when the workspace is a mess. That's the cost of bad context, made visible. The best bit is the end-of-level screen: your first messy run next to your clean one. Same job, same robot. The only thing that changed was the structure. That's the whole idea of ICM in one picture. Credit where it's due. The method is Jake van Clief's. This is just a way to play with it. Have a go, then tell me how I can improve it! https://claude.ai/code/artifact/52eee8c6-a5c2-401c-a2a0-8630848288ef