@derrickcchoi: Recently moved to Singapore, want to hear your thoughts on Codex: What improvements do you most want us to make? Where is it not working smoothly? English or Chinese is fine, just reply directly!
Summary
After moving to Singapore, @derrickcchoi is publicly soliciting improvement suggestions and user experience feedback for Codex, supporting replies in both English and Chinese.
View Cached Full Text
Cached at: 08/18/26, 08:30 AM
最近刚搬到新加坡，想听听大家对 Codex 的看法：最希望我们改进哪些方面？有哪些地方用起来不够顺畅？
中文或英文都可以，欢迎直接回复！
Similar Articles
@JinjingLiang: I have the feeling that Codex does a better job reviewing code & debugging when I prompt it in Chinese Need to run more…
A user observes that OpenAI's Codex performs better at code review and debugging when prompted in Chinese, and plans to run further experiments.
@reach_vb: hey friends at deepseek, if you have any feedback on codex please do let me know! hope you enjoy codex as much as I do
A tweet invites DeepSeek to share feedback on Codex, noting that Codex has been significantly used in DeepSeek's development, with approximately 20% of commits and PRs from Codex worktrees.
@sama: I am happy everyone is switching to Codex, but Tibo if you start rate limiting me or making me use worse models...
A social media comment expressing satisfaction with adoption of Codex while warning against potential rate limiting or model degradation.
@huangyun_122: Why lately when everyone discusses Codex and Claude Code, they all mention Codex original harness and Claude Harness? This makes me especially nervous, feeling like I'm behind by at least one weekend.
A tweet discussing the community's recent frequent mentions of Codex original harness and Claude Harness, with the author feeling like they might have fallen behind again.
@xiaogaifun: A Major Pitfall Our Team Encountered with Codex. I want to sincerely share a topic we discussed in our weekly meeting. This might be a common pitfall for many people using agent products like Codex. In short, if we just keep issuing commands and accepting suggestions from Codex without understanding or judgment, then these...
The team shares the problem of over-reliance on AI leading to a lack of deep understanding among members when using Codex. It emphasizes that humans should act as leaders of AI, not mere messengers, and need to understand the principles and logic, turning AI output into their own experience.