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

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

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

A folder without a CONTEXT.md is a folder the agent has to guess about, and it will. Loose files in the root are where structure goes to die. They arrive one at a time, so there is never a day you notice it happening. Every relative link resolving is the one worth having. Rename a file and every reference to it keeps pointing at nothing. No error, no crash, nothing turns red. The model reads around the gap and answers you anyway. It is the only failure of the three that leaves no trace. Attached is a shell script that checks all three. No dependencies, any Mac or Linux, run it from the workspace root. It exits 0 or tells you what is wrong. One thing before you trust it: break it on purpose. Delete a CONTEXT.md, run it, watch it fail, put the file back. A check you have never seen reject anything and a check that quietly stopped matching look identical from where you are standing. What else would you want it to catch?

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'