Library
Everything that is not an essay: interactive diagrams, talks, and the highlights and sources pulled out of the essays.
Illustrations 4
IllustrationAI Exposure — Theory vs Reality
Cross-referencing Karpathy's AI exposure treemap with Anthropic's observed coverage data, Stanford's entry-level impact research, and the measurability thesis. Four interactive views of the gap between what AI could disrupt and what it actually is.
IllustrationClaw Gateway Network Atlas
Six gateway architectures for AI agents, ranked from full control plane to no gateway at all. Interactive diagrams with animated data flows.
IllustrationThe History of AI: An Interactive Timeline
An interactive timeline of artificial intelligence milestones, from foundational research and philosophy to creative works and physical devices, overlaid with AI popularity trends.
IllustrationKata Containers Architecture
An interactive overview of Kata Containers architecture end-to-end, from the CRI runtime to the lightweight VM boundary.Talks 4
- From Autoresearch to Autoimprove: Generalizing the Agentic Experiment LoopAutonomous optimization loop for AI agents. Covers the autoresearch pattern, the improve.md format, goal-aware test generation, guard metrics, 10 domain templates, and real-world results on a RAG search engine.
- aimuxA terminal multiplexer for AI coding agents. Covers the visibility problem with multi-agent workflows, agent discovery, split-view tracing, annotations, OTEL integration, and MLflow export for evaluation.
- Agent Access ControlThe agent gateway for Kubernetes. Covers agent discovery, authentication, routing, credential injection, rate limiting, and MCP protocol support.
-
Agent RegistryA vendor-neutral registry for AI agents, skills, and MCP servers. Covers the problem of agent discovery, the registry architecture, and how agentctl works.
Highlights 53
Although the term is widely used by many people working in closely related areas, it defies attempts to produce a single universally accepted definition." — Michael Wooldridge & Nicholas Jennings, Intelligent Agents: Theory and Practice (1994)Every developer with an AI subscription and a GitHub account is now a one-person agency. They can ship in a weekend what used to take a team of four a month. And yet, most of them are broke.Skill-biased technical change is dead. What its successor looks like: measurability-biased technical change. The fault line is no longer how educated you are. It's whether your output can be measured. If it can, it will be industrialized. No exceptions.
All 53 highlights