Show HN: Do Codex skills save tokens? A six-run task-size benchmark

Six controlled GPT-5.6-sol runs reveal a task-size boundary worth replicating.
6 points by phelannguyen164 80 days ago codex-howto-benchmark.nguyenvantamdk2.chatgpt.site 1 comments
Summary not yet generated for this article.

Comments (1 of ) ⌛

Loading more comments... ⌛
Scroll down to load more comments
No comments available.
Type to search HN and engineering blog articles
Press Escape to close  |  ↑↓ to navigate  |  Enter to open