Predictable Swarm Scaling
Under suitable conditions, we can use simulation to roughly estimate the best structure for an agent swarm and its scaling law.
Blog
Notes and slides on topics I find interesting.
Posts
What Happened to AutomationBench?
Open models score well on AutomationBench; the scoring rule, unsound string-matching guardrails included, decides much of the ranking, and eighteen of its string guardrails fail runs a task owner would accept.
Introduction to Claude Code and Codex
A practical introduction to terminal coding agents: how Claude Code handles memory, permissions, custom commands, and MCP, how Codex differs, and how to run both side by side.