Harness vs One-Shot: Self-Review Iteration Makes AI-Generated JS Games Clearly Win
teortaxesTex · x · 2026-11-03
Developer loktar00 demoed 'Deepseek Flash' generating games in pure JS with all assets created from the prompt at runtime, comparing one-shot generation vs a harness run where the model self-reviews and chooses what to iterate on and fix — the harness clearly wins. He calls the model a fantastic scratchpad for quickly turning ideas into prototypes. teortaxesTex argues the community needs a full engine for Wasm games instead of such token-wasting test demos, noting iteration speed has vastly improved in under six months.
More from coding & agent
- 10,000 AI agents burned his API credits; 500 agents in 50 waves worked — Beneficial-Cow-7408 · 2026-11-03
- Walrus MCP Server connects AI assistants to decentralized storage — modelcontextprotocol · 2026-11-03
- News Volume Trends MCP queries news volume growth for any topic — modelcontextprotocol · 2026-11-03
- Pen ships a canvas plugin for Codex, adding design powers to ChatGPT — paw_lean · 2026-11-03
- Elicit engineers all use Ramp's Inspect — a credit card company builds a top coding agent harness — jungofthewon · 2026-11-03
- VibeArmory launches macOS private beta: monitoring and firewalls for AI coding agents — agf2007 · 2026-11-03