Opus 5.5 autonomously coded a fully procedural kaiju simulation in pure three.js over 3.5 hours
majidmanzarpour · x · 2026-09-24
To test creativity, the author issued a deliberately minimal prompt: 'Build a fully procedural AAA quality kaiju simulation in three.js using pure TSL and modern techniques.' Opus 5.5 then worked autonomously for 3.5 hours, producing a kaiju simulation written entirely in pure three.js code. The full prompt and an interactive demo artifact are public — a striking data point on long-horizon autonomous coding and creative capability.
Related event: Opus 5.5 Builds AAA Kaiju Simulation in 3.5-Hour Autonomous Run(2 posts)→
More from coding & agent
- Loom founder launches Roma 2.0, a shared to-do list that orchestrates AI agents — thetripathi58 · 2026-11-12
- Sosumi Eval: Apple Docs Access Lifts Coding Agent Pass Rates from ~33% to 94-98% — JordanMorgan10 · 2026-11-12
- CypherGuard fixes structurally wrong LLM Cypher queries, hitting 88.5% on CypherBench — JeremyCMorgan · 2026-11-12
- Building an End-to-End Hedge Fund in Python with Claude Code: A 5-Step Workflow — mdancho84 · 2026-11-12
- Jeff Dean: comfortable with engineers spending up to $10M/year on AI tools — deedydas · 2026-11-12
- Developer builds VladOS, a personal life dashboard, by just describing it to an AI agent — haltakov · 2026-11-12