-
Thinking Depth Regression unlisted
April 2026 — A Claude Code incident exposed what happens when adaptive reasoning under-allocates. The fix is not better prompts. It is verification at the boundary.
-
The Bitter Lesson of Agentic Coding
April 2026 — Invest in verification and goal-setting, not implementation control.
-
Agent-Hypervisors
June 2025 — An approach toward self-optimizing agent fleets.
-
LLM Inferencing Costs are Going to $0
March 2025 (updated April 2026) — The marginal price of intelligence is trending toward zero.