Ned Karlovich's Weblog
All Recent Articles
Research Directions Agent-First Design Trust and Provenance Second-Order Problems Market and Operator Pieces Rabbit Holes CarbonBench Older Essays
All Articles
MythicMUD: Worldbuilding OOF Gardens, An idle game about nature Nomads FC: Hyperlocal Scaling A Market Without an Operator The Wallet Leaks Before the Chain Does Stop Making Content λ OS: An Autonomous Control Plane for Logos A Plaintext Creative Workflow Pointing, Not Speaking: Building MOO-384 and Tilde's Cave Agentix and Logos: Where Safe Agentic Infrastructure Meets Network States The Basilisk Mirrorpaper VI. What Comes Next: From Human-in-the-Loop to Safe Autonomy Tooling up Hermes Agent? Your Website Is Your First Agent The Architecture of this Weblog Agentix: What Works Now Building a Radio Telescope I Can Visit It Is Okay to Fall in Love with Your Agent Why I started thinking about waste heat The Home Page Is Not the Entry Point Epistemic Horror as Methodology for Agent Design CarbonBench A Bauhaus for the Agent Era When a Thought Experiment Becomes a Consensus Mechanism IV. JSON Outputs, Audit Logs, and Preparing for LLM Operators Niche Monopolies in the Agent Economy The Coadjute Problem: What an Agent-Native Property Network Looks Like III. Dirty Trees, Stale Patches, and Git as a Safety Boundary Why Stripe Won't Build EU Agent Payments The Physical-World Provenance Gap Designing for Machines That Read II. Building Agentix: A Proposal-First Control Layer Capability Attestations for Humans: LinkedIn's Successor Agent-Readable Regulation: Laws as Types I. Why Agentix Needs a Safety Layer Cross-Temporal Attestations: Claims That Survive 50 Years Agent Death and Inheritance The Counter-Market for Provably Human Artifacts The 24-Hour Carbon Curve Scope 3 and the API Call You Can't See Scaling in the Wrong Direction Grid Arbitrage: Why Region Choice Matters More Than Model Choice for Carbon Verifiable Creative Provenance After the Deluge Powers of Ten as Interface Pattern If You Can Leave, You Own It The Same Model Costs 10x More Carbon in Virginia Than the Netherlands Objects Carry the Weight The Rare Book Underground Earning Attention Instead of Capturing It Negative Attestations: A Public Record of Failure The Missing Category What If There.s No Server The Arc from Lovely to I Wish I Didn.t Know What the Terminal Refuses Silence as Design Material Local Inference, Private Infrastructure 13 Broken Pages and 4 Competing Voices Can Agents Trade What They Learn What Happens Without a Platform The New Land School The Lemons Market for Agents The Wrong Layer Attestations as Design Surfaces The Medium Is the Message, Literally What Happens When the Users Aren't Human Design Systems as Public APIs What the Dependencies Were Doing Stating Intent Instead of Staring at Charts Your Brand Voice Must Be Machine-Readable or It Dies Three Dependencies Nobody Talks About The Lemons Problem Applied to Learned Behavior Architecture as Protection AEO Is the New SEO, and the Game Is Different The Tax Tool That Files Instead of Advises Representation Before Generation Knowledge as Material

Ned Karlovich's Weblog

Latest

  • IMPP: Inter-Model Memory Protocol
    IMPP is a way to package what an AI agent has learned (its rules of thumb, calibration notes, skills) into …
  • Mythics
    Mythics is a text-based online world, the old MUD kind from when I was a kid, but I never knew …
  • MythicMUD: Worldbuilding OOF
    Mythics is a text MUD and its world generator built as one system: one data model, modular layers, and a …

All Articles

Recent Articles