Cost-Quality Pareto for Coding Agents (May 2026)
Paying $5 per task no longer gets you the frontier. Qwen3.6-27B running locally hits 77.2% SWE-bench Verified at ~$0.04/task, within 10pp of Opus 4.7 for ~130x less money.
blog
Deep dives and field notes on local-first AI, agentic architecture, and what is actually working in 2026, with primary sources and reproducible benchmarks.
Showing 6 of 38 posts in Culture · clear
Long-form research articles with primary sources, benchmarks, and reference tables.
What is actually shipping out of the Boulder AI scene in May 2026, what is on the schedule for Boulder Startup Week, and why the Give First culture matters for agentic builders.
Agent Experience is the new SEO. Here is what it means, what changes, and the four-step audit to figure out how your product looks to the agents already using it.
The engineering math behind preventing an agentic loop from burning through your monthly runway in one night.
How to lead a codebase by stating intent instead of writing syntax, and the discipline that keeps it from falling apart.
Real numbers, real workloads, real break-even points. When local is the obvious answer, when cloud is, and the hybrid that wins for most teams.