How to SSH into an Otto, and how I got its OpenClaw Control UI working over Tailscale Serve.

A cautious, nuanced case for AI optimism: why safety, interpretability, bias, and alignment matter as much as raw capability.

I wired OpenAI's Codex into Claude Code as a consulting subagent for architecture reviews and tricky debugging.

Delegate implementation from Claude Code to Codex in an isolated worktree, then review the diff through an approval loop that keeps commits under your control.

How I use sentinel files to gate the risky moves my coding agents make.

How Ultraplan moves coding-task planning to Claude Code on the web for browser review, remote execution, or local handoff.

Compare Playwright CLI, Playwright MCP, and Chrome DevTools MCP to choose browser automation and debugging tools for coding agents.

How the Ralph Loop gives an AI coding agent a fresh context window for every iteration—and why that changes the workflow.

A three-axis framework—Forms, Functions, and Dynamics—for understanding and building modern agent memory systems.

Review Temporal's Developer Skill for coding agents: a sound foundation with gaps in actionable guidance, language awareness, and verification.

Explore the loop shared by AI agents and the production concerns around it: context compaction, loop detection, cost budgets, and graceful termination.

Agent skills are a context-management strategy for routing tasks progressively and reducing cognitive overload.

A technical walkthrough of building systems that run untrusted repositories, covering isolation, dependencies, network access, artifacts, and operations.

Design an AI gateway for routing, policies, and cost control alongside durable workflows that survive failures, pause for approval, and replay.

MCP servers return data. MCP Apps let them ship a UI alongside that data—so the tool author, not the client, decides how results look.