Nolan Lawson benchmarks the AI cost of JS frameworks: results mostly similar
hichaelmart · x · 2026-10-29
Microsoft Edge engineer Nolan Lawson published a benchmark measuring the "AI cost" of JavaScript frameworks, pushing back on the web dev community's habit of vibes-based claims. He argues that just as "the virtual DOM is fast" rationalized React adoption, claims that certain frameworks are "better for agents" are rarely backed by evidence.
The setup: build a small but non-trivial Pokémon app on the PokéAPI, have AI agents implement it with different frameworks, and compare cost and quality. Reposter hichaelmart notes results are mostly similar across frameworks, with Angular as the clear outlier, while Hono, Astro, and even vanilla JS rank near the top.
More from coding & agent
- GitHub's zeeg: worktrees are the poor man's sandbox for coding agents — rsasaki0109 · 2026-10-29
- Building with coding agents and middle management are wildly different skills — corbtt · 2026-10-29
- Replit's ViBench 2.0: top models pass only 49-65% of long-horizon builds — amasad · 2026-10-29
- Interactive 3D biology lesson built with Opus 5.5 and Three.js follows one breath — techartist_ · 2026-10-29
- Replit's ViBench 2.0: best models pass only 49–65% of builds, GPT-6.1 Sol leads — amasad · 2026-10-29
- Dev calls for task-level undo for personal agents, like database transactions — gethackteam · 2026-10-29