saski

in control systems you're constantly trying to go from current state of the world -> desired state of the world. A canonical educational example is like trying to balance a pole on a cart (see link below for video) So when thinking about how to balance that pole, we can imagine the state being the angle of the pole. And we can either move the cart left or right to balance it. The first thing we can do is take the difference: how far are we from it standing straight up? That's the "P" part in PID (proportion). But if you only have this, then you'll find that there's kind of a "point of no return", as soon as the pole falls just enough, the system is borked it will fall. So to help with that you can add the 'D' part (derivative): if the error is increasing quickly, we may need a stronger correction. But even this isn't quite enough; you'll find yourself in a game of lots of fast, small corrections (kind of a constant over-shooting back and forth, never quite reaching balance). So we add the 'I' part (integral): dampen your corrections based on how error has accumulated over your past actions (so as you get closer, less error you slow down... acts sort of like a learning rate schedule) Your thermostat example just got me thinking that there's maybe a broader analogy here, and I wonder if there's some insight into how to design our controls around the agents with an expanded analogy :) statusfailed.com/blog/2022-1…

Introducing the Open Knowledge Format (OKF), an open specification that formalizes the LLM-wiki pattern into a portable, interoperable format. AI is only as smart as the context we give it. As we build more advanced, agentic AI systems, they need accurate metadata and context to be useful. But in most organizations, that context is locked inside fragmented data catalogs, isolated wikis, scattered code comments, or the minds of senior engineers. Every time a new AI agent is built, teams are forced to solve the exact same context-assembly problem from scratch. To solve this, we've announced OKF, a vendor-neutral, open specification that formalizes the "LLM-wiki pattern" into a portable, interoperable format. It provides a standardized way to represent the enterprise knowledge that modern AI systems rely on. — Just markdown: readable in any editor, renderable on GitHub, indexable by any search tool — Just files: shippable as a tarball, hostable in any git repo, mountable on any filesystem — Just YAML frontmatter: for the small set of structured fields that need to be queryable: type, title, description, resource, tags, and timestamp We’ve also shipped reference implementations to help you hit the ground running, including an enrichment agent for BigQuery, a static HTML visualizer, and live sample bundles on @github → goo.gle/4uGvAEe ➕ Knowledge Catalog can now natively ingest OKF! Stop reinventing data models and building bespoke integrations for every new AI tool. Here's more about how OKF works → goo.gle/4uGvBbg