Answered raw tape
D 5 · C 4 · P 4 · Cm 3 4.15
Q Wait, hold on, you said self-forming. How does this end up being a self-forming entity?
A Yeah, so self-forming is actually, when you think about it, and this is fascinating, um, I'll take another, you, you mentioned mold book, I'll just, you know, pick up on OpenClaw, but if you look at OpenClaw, the way it's actually, so OpenClaw is, um, Yeah. Let's put it this way, is a, is a state-of-the-art agentic loop, right? So, uh, the agent can reason, but the way it's doing its reasoning, based on memory, based on context, based on skill, also sound and personality, is actually going to, uh, spawn sub-agents, uh, through reasoning, and that is self-forming. So, basically, the, the, the set of agents, and again, this is just taking a small popular example with, uh, OpenFlow, but think about it happening at a much bigger scale, you know, within corporates, with a much higher level of security, And, and, um, uh, um, higher level of security and higher level of certification, if you want. And, uh, and that's it. So the, the ability for these, uh, agentic system to reason and to decide which agents they need to bring in, that's why it's so important to be able to discover agents. That's why we have the directory feature in, in agency, because that's one of the fundamental building block. This, you know, look at the skills you need, discover these agents and bring them along in your mission. Uh, and task them with portion of the, the, the, the, uh, the plan that you've just for…
AI assessment note: “spawn sub-agents, uh, through reasoning, and that is self-forming”
Answered raw tape
D 4 · C 4 · P 4 · Cm 3 3.85
Q How do you, how do you control that? How do you control that? Because it seems like a path to runaway AI.
A Yeah, so, so this is where you need, again, and, and your question is spot on. Controlling this is part of the, um, cognition challenges that we've identified, because you need to put a lot of, um, guardrails around this. And so you can control it at different level. So if you think about, um, the, the, the pure connectivity level, so again, stuff which is out there, and when I say it's out there, I'm, I just want to make sure, uh, folks listening to the podcast understand this is very concrete. Go to, uh, agency.org, or, you know, find the corresponding Git, and you'll find a ton of code. It's, it's not concept, right? You have a lot of code. We have example application. We have something called Coffee Agency. You can go there. It's a, You know, the equivalent of a stock shop, you know, for Kubernetes, this is how to get started, and we exercise the different agency function in a little example application, and then we have more advanced examples there as well. And so, to put things under control, you need to, you need to control connectivity. So, for that, um, we have, uh, first of all, we can very strictly control, uh, who's talking to who, right? Just like in, there is a fundamental, and this is where applying, um, Networking vision to this technology is so powerful because, um, with networking, you might be, uh, familiar with, um, uh, techniques or technology called, uh, n…
AI assessment note: “to put things under control, you need to, you need to control connectivity”
