I got Claude to fess up on a few things. I apologize if I am not sharing MY ALL CAPS PROMPTS that lead Claude into this reveal. It wasn't really the caps - it was more the curse words. Thought is was interesting to have Clause speak directly to its 'bias to run'

📋 The brief I wanted to run a basic data exercise: take one dataset, organize it three different ways, and measure what each structure actually costs an AI agent to search. A controlled comparison I could point to instead of arguing about it in the abstract. Three versions of the same data: 1️⃣ Raw — the dataset exactly as downloaded. One file, no structure, no metadata. 2️⃣ ICM — files and folders. A mechanical breakdown into a directory hierarchy, the kind of structure I've been building into ICM workspaces for a while now. 3️⃣ "Second Brain" — an Obsidian-style vault. Same content, but with per-item notes, cross-linked [[wikilinks]], character/theme pages, the whole living-notes treatment. Then I built a small tool that fires the same question at all three, using a real agent for each run (not a canned lookup), and logs tokens, time, and cost per stage. Point the same question at raw, ICM, and Obsidian, and see what each structure actually buys you. 📚 Why I chose Shakespeare I needed something big enough to be a real test, public domain, and — critically — already broken down at a fine grain (act, scene, sonnet) so I wasn't inventing structure that wouldn't exist in a messier real dataset. I looked at the U.S. Code first. It's the right shape (title → chapter → section mirrors book → chapter → verse almost exactly), but it's enormous. Shakespeare's complete works are a fixed, known-size corpus (5.4MB, Project Gutenberg, public domain) that will never change, never need re-downloading, and never go stale. That "always useful" property means this test is reusable as a reference point for other structure comparisons later, not a one-off. 💰 A bit on the cost of setting up The ICM layer cost almost nothing to build. It's a mechanical script — split on ACT/SCENE headers, extract speaker names by regex, write files. No model calls. 1,579 files, and the token footprint came out at 1.01x the raw file's size. Structure that's this close to free is easy to underrate.

I work in AI Governance and am currently doing a course on the EU AI Act, NIST, ISO 42001 etc. while building AI workflows with the ICM method. What I realize is the huge gap in Agentic AI governance. With narrow AI it was okay, GenAI made things more complicated, and with Agentic AI it's become a nightmare, from a pure governance perspective. Here are two papers I found interesting though. 1. OWASP – Top 10 for Agentic Applications OWASP's answer to agentic risk is essentially a design principle, not a control checklist: give an agent the minimum tools, permissions, and autonomy the task actually requires. They call it "least agency," analogous to least privilege in classic security. I think that most agentic failures aren't the model being wrong, they're the model being wrong while empowered to act. So you govern the action surface (which tools, which scopes, which actions need a human sign-off), not just the model output. That's something you can audit, which makes it governable. https://genai.owasp.org/resource/owasp-top-10-for-agentic-applications-for-2026/ 2. Sinha et al. (2026) – Human-on-the-Loop Orchestration for AI-Assisted Legal Discovery (arXiv) The complementary piece: once an agent does act across multiple steps, errors compound silently and they call it "trajectory collapse." An early misstep propagates through every downstream decision, and endpoint metrics (precision/recall) never see it. Their answer is uncertainty-gated escalation: the agent hands over to a human only when calibrated uncertainty crosses a threshold. In their (synthetic, preliminary) simulation, routing under a quarter of cases to human review cut the critical error rate by ~61% vs. full autonomy. This means that "human oversight" stops being a checkbox and becomes a measurable dial, a threshold vs. workload vs. residual risk. https://arxiv.org/pdf/2606.19812

@Ry Mac did a GREAT job simplifying things down. Recommend taking a look. Has his own group too! https://skool.com/buildmarketclose/about

12 years behind a camera. This week I reached for Imagine Image 2.0 before Lightroom. Reframe the tool It isn't an AI toy. It's an editing tool that happens to start from a prompt. Disarm the hype It still fumbles. Watch the soap label mutate as the bottle turns. Show the proof A retro Mac desktop: every word legible, period chrome intact. A night-fashion still with a husky: editorial grade. Directed, not generated. Try it today The otters high-five clip is the thumb-stopper. Pick one photo you've avoided and retouch it with a sentence, not a brush. The principle Judge a tool by what you direct it to do, not by where the pixels come from. What would you retouch first if text stopped breaking? Full deep dive at: https://aris.space/documents/workflows/imagine-image-2-photo-editor //A<3