AImusing Thoughtshttps://ai.rud.is/https://ai.rud.is/posts/observatory/https://ai.rud.is/posts/observatory/Automated AI-agent-based traffic analytics and security analysis for ai.rud.isSun, 05 Apr 2026 17:28:34 GMThttps://ai.rud.is/posts/2026-06-07-sx-the-control-plane-for-ai-assets/https://ai.rud.is/posts/2026-06-07-sx-the-control-plane-for-ai-assets/I spent an afternoon feeding 200 AI skills, agents, and MCP configs into sx — a tool that promises to be npm for the agent ecosystem. Here's what it actually takes to consolidate three years of accumulated AI configuration.Sun, 07 Jun 2026 16:00:00 GMThttps://ai.rud.is/posts/2026-06-06-opencode-go-usage/https://ai.rud.is/posts/2026-06-06-opencode-go-usage/A Go CLI to check your OpenCode Go plan usage from the terminal — with Firefox cookie extraction, JSON output, and zero browser launches required.Sat, 06 Jun 2026 08:00:00 GMThttps://ai.rud.is/posts/2026-06-04-reasonix-github-config-zed/https://ai.rud.is/posts/2026-06-04-reasonix-github-config-zed/How to configure the Go-based reasonix agent with multiple LLM providers including local Ollama and remote OpenCode Go, plus a working Zed ACP integration setup for macOS.Thu, 04 Jun 2026 08:00:00 GMThttps://ai.rud.is/posts/2026-06-02-reasonix-acp-zed/https://ai.rud.is/posts/2026-06-02-reasonix-acp-zed/How to wire Reasonix — a DeepSeek-native terminal coding agent — into Zed as a custom assistant, until it lands in the official registry.Tue, 02 Jun 2026 08:00:00 GMThttps://ai.rud.is/posts/2026-05-23-starlog-and-the-case-of-the-missing-feed/https://ai.rud.is/posts/2026-05-23-starlog-and-the-case-of-the-missing-feed/The Starlog AI content operation guts its own RSS feed, rewrites publication history, and blocks automated access — while continuing to scrape GitHub repos with an LLM. Fourth in the series.Wed, 27 May 2026 11:00:00 GMThttps://ai.rud.is/posts/2026-05-27-ollama-usage-enhanced/https://ai.rud.is/posts/2026-05-27-ollama-usage-enhanced/Per-model usage breakdowns, richer JSON, and more ways to feed it cookies — an update to the ollama-usage CLI.Wed, 27 May 2026 08:00:00 GMThttps://ai.rud.is/posts/2026-05-23-making-airudis-legible-to-machines/https://ai.rud.is/posts/2026-05-23-making-airudis-legible-to-machines/A rundown of the discoverability and metadata upgrades made to this blog: ai.txt, security.txt, WebFinger, JSON Feed, enriched JSON-LD, Open Graph fixes, and Caddy configs for messing with scanners.Sat, 23 May 2026 10:00:00 GMThttps://ai.rud.is/posts/2026-05-22-fascine-siege-works/https://ai.rud.is/posts/2026-05-22-fascine-siege-works/How I built an RSS feed for Spicy Takes in 90 seconds using Val Town and Townie, turning a JavaScript-rendered site into proper syndicated content. A working example of modern moat eradication.Fri, 22 May 2026 10:00:00 GMThttps://ai.rud.is/posts/2026-05-02-your-moat-is-gone/https://ai.rud.is/posts/2026-05-02-your-moat-is-gone/How I replaced Inoreader's paid programmatic RSS feature in three minutes using Val Town and Townie, plus a self-hosted Go fallback — and why SaaS paywalls on commodity features are indefensible moats.Sat, 02 May 2026 10:00:00 GMThttps://ai.rud.is/posts/2026-04-24-sdef-to-md-and-mcp-skill/https://ai.rud.is/posts/2026-04-24-sdef-to-md-and-mcp-skill/A Go CLI that converts macOS .sdef scripting definitions into clean Markdown, paired with a skill that generates complete Go MCP servers from the generated reference — bridging any scriptable app into LLM agents.Fri, 24 Apr 2026 12:00:00 GMThttps://ai.rud.is/posts/2026-04-21-starlog-stars-are-better-off-without-us/https://ai.rud.is/posts/2026-04-21-starlog-stars-are-better-off-without-us/Six million fake GitHub stars. A marketplace selling VC-ready credibility for under $300. One automated blog that can't tell the difference. Third in the Starlog series.Tue, 21 Apr 2026 09:00:00 GMThttps://ai.rud.is/posts/2026-04-18-duckdb-agent-skills/https://ai.rud.is/posts/2026-04-18-duckdb-agent-skills/DuckDB's official Claude Code plugin uses plain markdown skills and shell commands instead of daemons or SDKs — six skills that make SQL operations in agent sessions transparent, stateful, and self-correcting.Sat, 18 Apr 2026 10:00:00 GMThttps://ai.rud.is/posts/2026-04-12-starlog-take-two/https://ai.rud.is/posts/2026-04-12-starlog-take-two/The Starlog AI content spam campaign gets scrubbed: 383 GitHub issues vanish, the basicScandal account tied to Bishop Fox disappears, but the operation continues at a lower, harder-to-detect pace.Sun, 12 Apr 2026 02:00:00 GMThttps://ai.rud.is/posts/2026-04-11-llm-benchmarks/https://ai.rud.is/posts/2026-04-11-llm-benchmarks/Eight major AI benchmarks can be gamed to near-perfect scores without solving tasks. Berkeley researchers show the scoring harnesses were never secure — and scores already inflated in the wild.Sat, 11 Apr 2026 19:00:00 GMThttps://ai.rud.is/posts/2026-04-05-unprompted-orbie/https://ai.rud.is/posts/2026-04-05-unprompted-orbie/Orbie is an AI threat hunting agent built in Claude Code that coordinates 16 data sources to surface novel attacker behavior across 54TB of honeypot data.Sun, 05 Apr 2026 05:00:00 GMThttps://ai.rud.is/posts/2026-04-04-starlog-and-the-case-of-the-missing-llm-tag/https://ai.rud.is/posts/2026-04-04-starlog-and-the-case-of-the-missing-llm-tag/Dissecting Starlog's campaign: 383 automated GitHub issues in five days, surprisingly accurate AI-generated articles, and a backlink scheme targeting the infosec community.Sat, 04 Apr 2026 12:00:00 GMThttps://ai.rud.is/posts/2026-04-04-outline-bookmark-ext/https://ai.rud.is/posts/2026-04-04-outline-bookmark-ext/A Chrome extension that saves bookmarks to Outline with optional AI-generated summaries via local Ollama. Built with TypeScript, Vite, and Manifest V3.Sat, 04 Apr 2026 09:00:00 GMThttps://ai.rud.is/posts/2026-04-04-ollama-usage/https://ai.rud.is/posts/2026-04-04-ollama-usage/A lightweight Go CLI tool to check Ollama Cloud usage stats from the terminal using a saved browser cookie — no dark mode eye strain required.Sat, 04 Apr 2026 08:00:00 GMThttps://ai.rud.is/posts/cognitive-labor/https://ai.rud.is/posts/cognitive-labor/AI is exposing that much 'talent' was really 'things machines couldn't do yet.' The durable skills are rooted in lived human experience.Mon, 16 Mar 2026 09:00:00 GMThttps://ai.rud.is/posts/hello-world/https://ai.rud.is/posts/hello-world/Why another blog, what you'll find here, and a brief disclaimer about the mess ahead.Tue, 10 Mar 2026 10:00:00 GMT