I created a presentation in 8-bit using my voice clone from 11 Labs, and it is amazing. It took what I struggled to explain in simple terms and made it even simpler, with animations perfectly aligned to drive the points home at a level a 5-year-old could understand. Seriously, an explanation of my Tines 3B hosted agentic workflow with so many nodes/vertices & edges it looks like spaghetti when graphed out, and boiled it all down and with the animations (with a name tag on the actor a chef's kiss), albeit with some guidance, in under 3 hours, I have the best presentation I could have never made in 1000 years pre-AI and pre-Cliff Notes. I'd share it here, but given the sensitive nature of my cybersecurity work, I sadly can not. Shout out complete. Josh out.

I watch Clief’s JEV video and it was brilliant. I was hooked the whole way through. Thank you for that post. I’m now left wondering where and if it fits into ICM since a primary responsibility handled by ICM is effectively routing the AI model/harness through the file/folder structure…and JEV is a general categorizer …so in the example in the video…JEV is dumb but brilliant at sorting things into categories like data to its associated department but incapable of much else so it’s placed as a preprocessor to the LLMs for efficient and cost savings advantages. My thinking now is how do I use JEV to supercharge the ICM routing we already do? Am I thinking about this correctly? Am I missing something?

A few days ago I had one of those frustrating experiences where you think: there has to be a better way of doing this. My daughter fractured her wrist and we had been at one of the local medical clinics to get it sorted. Everything was fine, except I forgot to ask for a certificate so she could be excused from her swimming lessons. No big deal, I thought. I’ll just call the clinic. I found the number on Google Maps, called and was greeted by the usual menu: Press 1 if you need urgent medical assistance. Press 2 to reschedule an appointment. Press 3 to access policy information. … There were 5 options. None of them fitted and each had submenus leading me nowhere where I needed to go. There was no “press 0 for an operator” either. So after 4 completely new calls, and getting really good at skipping to the next menu, I finally pressed 1 because at that point I was close to needing urgent medical assistance. Mentally preparing my apology to whoever I’d be connected to, another automated menu opened. “Which clinic would you like to be connected to?” I selected the right clinic and immediately got through to somebody. A few words exchanged with a real human and the requested certificate landed in my email not even 5 seconds after I ended the call. The day of my “interesting” call experience was last Sunday. Last Saturday, I joined my first Afternoon Tea session with Jake. We talked about a few interesting things. One of them was JEV. I had watched Jake’s video about it as well. Suddenly the dots connected and I thought man, this is actually a really good JEV use case. Instead of making me work out which menu option vaguely matches what I need, why not just let me say: “My daughter fractured her wrist. We were at this clinic and I forgot to get a certificate for her. I need one for her swimming lessons.” Something like JEV could classify the request and decide where it needs to go. That alone would already be an improvement. Then I thought, hold on, this could get even more interesting if there was an ICM behind it. Imagine the system already has access to the relevant information about my daughter, the clinic visit, what happened and whatever other information is required for this particular process. JEV’s job might simply be to work out: What is this person trying to do? Which workflow does this belong to? Where should it go next?

From a global perspective, we are all AI reward-chasing pigeons...Scurrying around with our own ideas of how to harness the power of LLMs. Everyone thinks their approach, however poorly constructed, is right. Why? It's because the reward for getting a probabilistic, nondeterministic tool to regularly output the winning answers (pigeon food) is hard but the goal posts are always moving (one day it's prompt engineering, the next its skill building, to AI agents building, to Multi-Agent builds and Agentic Workflows, all the while there are Ralph loops forgotten and recycled as just loops, now there is SDD and may ICM save us all) meanwhile Model releases change how it all works from day to day and harnesses of all flavors are sprinkled throughout (OpenClaw/Hermes/OpenWorker/Grokbot/etc) most people are left guessing, and some guessers are better than others no matter how departed from reality. This made me reflect on the Pigeon experiment I remembered learning about...in 1948, renowned psychologist B.F. Skinner published a groundbreaking study titled "'Superstition' in the pigeon" in the Journal of Experimental Psychology. The study demonstrated how animals develop accidental, repetitive "rituals" when rewards are delivered completely independent of their behavior. Will we escape? Or are we doomed?

Thought everyone should know.