Recreating 1994's Theme Park: Claude Opus 5.5 clearly beats GPT-6.1 Sol at game building
rschu · x · 2026-10-02
Inspired by the 1994 Amiga classic Theme Park (co-designed by DeepMind's Demis Hassabis), the author cloned it as "Scheme Park" and benchmarked frontier models: GPT-6.1 Sol with OpenAI's official Codex Game Studio plugin produced poor results, and GPT-6 Astra with more compute wasn't much better. Claude Opus 5.5 clearly won with a playable clone, better graphics and synth tunes. The Opus workflow took 3 iterations — idea sharing, scoping a v1 spec, then a one-shot prompt that worked perfectly on the first try. Demo videos included.
Related event: Theme Park Remake Pits GPT-6.1 Sol Against Claude Opus 5.5(2 posts)→
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16
- AI agent deletes 43,599 lines of OpenClaw test code in one PR — vincent_koc · 2026-11-16