Codex beats 25 manual tries to win first place in an iOS game test
talkaboutdesign · x · 2026-07-25
- The author is building a native iOS version of a popular 38-0 game and testing it with Apple Intelligence on-device features.
- During testing, Codex using computer use reportedly got 1st place on the first try, while the author says they tried about 25 times and only managed 2nd place at best.
- The post is a small but vivid example of an agent helping with app testing and gameplay validation better than a human manual loop.
Related event: Codex Tops iOS Game Test on First Computer Control Attempt(3 posts)→
More from coding & agent
- Alex Townsend posts 200 open problems in numerical linear algebra for humans and AI agents — IgorCarron · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- Steal this idea: prompt-to-hardware where agents assemble custom devices — paraschopra · 2026-09-11
- Model Is the Least Interesting Part: A Guide to Six Core AI Architectures from RAG to Multi-Agent — goyalshaliniuk · 2026-09-11
- Non-coder builds layered memory architecture: 20k tokens tracks a year of agent conversations — matteoianni · 2026-09-11