Pelican-riding-a-bicycle benchmark turned into a playable game via 5-wave multi-agent loops
GlennCameronjr · x · 2026-11-11
agenticjay took Simon Willison's "pelican riding a bicycle" benchmark way too far: using Gemini 4 Carbon and a /swarm in antigravity, five waves of multi-agent critique loops produced a playable game set on the Mountain View campus. Subagents generated Nano Banana and Omni references to rig assets in headless Blender, wired Three.js bike physics and custom WebGL2 shaders, and produced procedural Web Audio SFX with a Lyria track.
More from coding & agent
- No Claude account? This DSH plugin lets you try Claude-style Whiteboards anyway — dotey · 2026-11-11
- Running 6 concurrent ds41-flash agents: persistent enough to need pi-durable coordination — dbreunig · 2026-11-11
- OpenAI roundup: architecture details of four GPT-Live voice agent builds — pbbakkum · 2026-11-11
- Ex-Apple keyboard engineer Ken Kocienda open-sources Tug, a macOS AI coding app in beta — Scobleizer · 2026-11-11
- Carbon tops Abundant Labs agent benchmark with 14/20 vs Opus 5.5 and GPT-6 — amankhan · 2026-11-11
- VS Code Copilot falls back from Computer Use and Python to PowerShell + COM to build an Excel workbook — dfinke · 2026-11-11