Codex beats a developer’s best manual iOS game test on its first computer-use run
talkaboutdesign · x · 2026-07-25
Codex wins an iOS game test on the first try during computer-use testing
A developer says they are building a native iOS version of a popular game with Apple Intelligence on-device features. During testing, Codex used computer use to play the game and finished 1st place on the first try.
- The developer says they tried about 25 times manually.
- Their best manual result was only 2nd place.
- The post is a concrete anecdote about Codex handling app testing through computer control.
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