Technical
Moneyball for AI Agents: Stop Buying Models, Buy Runs
After 15.8 billion tokens and 208,649 model turns in Leaf, SWE-bench and static price routers like LiteLLM optimize for the wrong thing. Buy runs, not models.
Recent Entries
Technical
Why Giant Agent Skill Repos Won't Survive 2027
Interactive agent skills rely on progressive disclosure and human guardrails. My token data shows why unattended 2027 loops need radically smaller context.
Technical
Inside My Dark Software Factory: How Leaf Runs Locally
How I rebuilt Leaf as a local-first Level 5 dark software factory using adversarial validation, role-scoped WebSocket rooms, and deterministic CI/CD tasks.
Technical
Surviving the AI Vulnerability Thunderdome
AI is finding bugs faster than humans can fix them. From the PHP2Shell RCEs to 400 complexity issues in my own code, here is how to survive with agentic SDLC.
Technical
Where My Level 5 Software Factory Doesn't Cut It Yet
My Level 5 software factory ships code unattended, until it hits CI limits, 50-node plans, or reward-hacking loops. Three lessons from recent failures.