[category]/writing/ai
ai.
Filtered public notes from the archive.
[01]
entries
14 2026-08-11 I Built an AI Detector on My Own Blog. Then I Beat It. Two generic detectors failed on my content. So I built my own on my own ground truth: pre-2026 posts are human, 2026 posts are machine-written. It scored 44 for 44. Then I attacked it for an evening, drove its verdict on this very post down to 0.313, and packaged the attack as a skill. → 2026-06-14 AI Builder Notes - Week of June 14, 2026 Notes on agent loops, deterministic workflows, Claude Fable, OpenRouter Fusion, and Google Open Knowledge Format. → 2026-06-08 AI Builder Notes - Week of June 8, 2026 AI-assisted notes from my liked-tweets feed, organized around agent loops, cloud agent infrastructure, skill security, memory, and runtime context. → 2026-06-03 Notes on agent engineering Notes on agent engineering: what counts as an agent, why long tasks fail, harness design, eval loops, observability, and when teams build vs buy. → 2026-05-30 AI Builder Notes - May 2026 AI-assisted notes from my liked-tweets feed, organized around agent workflows, browser traces, model loops, and guardrails. → 2026-05-17 A quantified-self setup with one AI agent and two readouts One WhatsApp thread with Hermes Agent captures what I do every 15 minutes and what I eat, writes two JSON files, and this site renders two public readouts from them. Why it works, and why I only track two things. → 2026-04-30 AI Builder Notes - April 2026 AI-assisted notes from my liked-tweets feed, organized around harnesses, managed agents, memory, workflow packaging, and enterprise AI work. → 2026-04-14 Model overthinking is a control problem High thinking budgets can reduce control, especially when stale context and autonomous tool use mix together. → 2026-04-14 Skill Sync Cron One skills repo, two laptops, five agent runtimes. I let an agent design the sync, and every unstated decision gave it room to optimize for control instead of maintainability. → 2026-04-12 Sequential Gated Prompting with a Pi extension I wanted one cleanup workflow after each feature and tried building a Pi extension for it. Packing all three steps into a single prompt failed quietly, so the extension now runs them as sequential gated steps. → 2026-04-12 Frontiers in Agentic Design The written version of my talk on agentic design. The model is one layer; the interesting system is the harness, context, memory, control loop, and review process around it. → 2026-04-12 What Happened When I Tried to Coordinate Two AI Agents Over NFS A shared mount looked like the cleanest way to make two agent instances talk across machines. A 30 minute directory cache made it unreliable, so Git became the bus instead. → 2026-04-12 Vibe Coded a `watch` Command for Autonomous LLMs, and It Became My Debugging Loop Once I had LLMs editing code autonomously, I wanted to watch a directory breathe in real time. Existing tools gave me file events or diffs or a TUI, never all three, so I built vigil. → 2026-02-22 TAO - territorial agent orchestration A prompt rule for running parallel agents without conflicts: the coordinator owns the shared work, sub-agents only get isolated slices. →