ATRIUMsearch → argument graph
ClaimArticle

Posing the exact same game-building prompt to Codex Desktop running GPT-5.6 Sol Ultra produced a much better game than Claude Fable 5 did.

The author ran the exact same Raccoon Heist prompt on Codex Desktop with GPT-5.6 Sol Ultra (which aggressively uses sub-agents) and got a much better game than with Claude Fable 5. ✦ AI generated

Author · Simon Willison's Weblog · 2026-08-07 · original ↗

I decided to pose the exact same prompt to Codex Desktop running GPT-5.6 Sol Ultra - the mode where Sol makes aggressive use of sub-agents - to see how it would do. It produced a much better game! Here's Moonlight & Mayhem - GitHub repository here, including the textures and prompts it generated using gpt-image-2.

Read full article ↗excerpt · fair-use quotation

Around this claim