Same prompt, same game: Sonnet 5.5 makes it run, Opus 5.5 makes you keep playing
victor_explore · x · 2026-09-29
A user gave two models the same prompt to build a game: Sonnet 5.5's version "runs", while Opus 5.5's version is something they "wanted to keep playing" — a vivid demo of the quality gap between tiers of the same model family in creative coding.
More from Models
- Leaked OpenAI 'dot' details show raising phone to ear triggers ChatGPT Voice — koltregaskes · 2026-09-29
- Google to replace Gemini Gems with Skills starting November 17 — mark_k · 2026-09-29
- Carla v0.1.0: a local llama.cpp loom TUI for growing AI characters — max_paperclips · 2026-09-29
- Leaked OpenAI DevDay reveal called 'just a Grok bot / Meta Muse rip-off' — gaganghotra_ · 2026-09-29
- Running Jev at high frame rate with full-state snap inferences makes it a true System 1 — mathemagic1an · 2026-09-29
- OpenAI model naming rumor: Dots, Orbit and 'o' said to be in the mix — mark_k · 2026-09-29