Harness Engineering in 2026: Techniques Beyond MCP
The named harness engineering techniques of 2026: ratchet rules, Ralph loops, spec-driven development and evaluator agents, with the cost of each.
Chronological archive · page 5 of 10
Independent analysis of the systems, prices and markets behind artificial intelligence.
Archive
The named harness engineering techniques of 2026: ratchet rules, Ralph loops, spec-driven development and evaluator agents, with the cost of each.
ZCode, Antigravity 2.0, Grok Build, Warp, and Zed all changed in 2026. Here is what actually shipped in each new agentic code editor, and what it costs.
Benchmark saturation is when top AI models bunch so close to the ceiling a test cannot rank them. Why MMLU hit this wall, and the harder replacement is next.
Claude Fable 5 returns after a US export-control suspension. Here is the $10/$50 pricing, the SWE-Bench Pro and FrontierCode scores, and what it means.
Claude Sonnet 5 ships at $3/$15 per million tokens, intro $2/$10 through August 2026. What changed versus Sonnet 4.6 and Opus 4.8, and the cost per task.
Kiro gives a free tier of 50 credits and Pro at $20 a month for 1,000. What a credit actually buys, the Auto versus pinned-model savings, and how overage works.
Windsurf became Devin Desktop on June 2, 2026, pricing unchanged. Cascade retires today. The real cost shift is what got bundled into the same $20 plan.
Your Claude Code session cost $47 in tokens. The real cost was $470. This is the math your dashboard does not show.
RAM prices roughly tripled in 2026 as AI memory demand starved consumer DRAM. Here is where the trend is heading and whether to buy now or wait.