OpenAI 征集 Codex 日常使用体验改进建议

My suggestion is not to replace the current compact approval prompt. The compact prompt is still good for quick, small changes. However, there should be an “Expand review” or “Open full diff” button that opens a larger review view before the changes are applied. Ideally, this expanded view could reuse the same full diff/review experience that Codex already provides after changes are applied, but make it available earlier in the approval flow. That way, users can properly inspect the proposed changes before accepting them. For example: Keep the current compact prompt for quick approvals. Add an Expand review button. When expanded, show a full diff viewer with the changed file list and side-by-side diff. Keep the same actions: Approve, Reject, and Ask Codex to revise. [...] For multi-file edits, show the changed files clearly in the sidebar. For simple edits, keep the experience lightweight. This would make strict approval mode much more useful, because users could actually revie

April 16, 2026 # Codex for (almost) everything We’re releasing a major update to Codex, making it a more powerful partner for the more than 3 million developers who use it every week to accelerate work across the full software development lifecycle. Codex can now operate your computer alongside you, work with more of the tools and apps you use everyday, generate images, remember your preferences, learn from previous actions, and take on ongoing and repeatable work. The Codex app also now includes deeper support for developer workflows, like reviewing PRs, viewing multiple files & terminals, connecting to remote devboxes via SSH, and an in-app browser to make it faster to iterate on frontend designs, apps, and games. ## Extending Codex beyond coding [...] ## Working across the software development lifecycle The app now includes support for addressing GitHub review comments, running multiple terminal tabs, and connecting to remote devboxes over SSH in alpha. It also lets you open f

Codex is much better when you show it what “good” looks like inside your repo. If you want a new screen, point it to an existing screen you like. If you want a new test, point it to a similar test. If you want a new service, show it the service pattern already used elsewhere. This avoids the classic AI problem: technically correct code that looks like it came from a different project. Most codebases have local style. Not just formatting, but small decisions. How errors are handled. How files are named. How state is passed around. How UI components are structured. How logs are written. How tests are organised. Codex can infer some of that, but it does much better when you explicitly anchor the task in examples. A prompt like this works much better: [...] One of the biggest traps with AI coding agents is giving them tasks that are too large. It is tempting. The agent seems powerful, so you ask it to “refactor the whole save system, improve the UI,

So, obviously, since we selected 9:00 a.m., it'll run again and again and again at 9:00 a.m. every single day and give you a new newsletter to send out to your audience. Now, we can also add another automation that can send out the email automatically to our email list. And all you have to do for that is just do the same thing we just did, click new automation, and ask Codex to send the email that it comes up with to our list. Now, while it's coming up with the newsletter, we can actually see that the design of the landing page could use some improvements. So, as we know, we have to ask Codex to improve it. So, either in a new chat or within the project, you can tell Codex to go over the landing page you created, look at the UI, which is the user interface, read the copy, which is the [...] page, it did a ton of work for a whole 10 minutes and improved every single aspect of it. So, it improved the copy, it improved the visuals, and it made it a lot easier to use. Now, as I mentioned e

system. And so, you know, like you can constrain it to a folder. You can disable network access. We're giving a lot of enterprise controls. I think this is very key to continue to expand from there. There's also investments that we've done. It's on our alignment blog post. Uh, we call this feature auto review, where we have created an agent that is capable of reviewing the actions of the primary agent. And the way it works is that it the primary agent codex is incentivized to do the work for you. At times, it might take an action that is, you know, maybe a little bit risky. And so, you have another agent that sort of reviews every action that it's taking and flags and stops it if it's like a high risk thing. And, you know, I expect like more innovations like this will be necessary. [...] be. Mhm. So, the more and better context gives you more and better results. And some of that context is in your head. And so, [snorts] it's your goals. It's things you've experienced that are not in th

My morning routine now starts with batching disparate maintenance tasks across our codebases. I'll queue up 4-5 Codex tasks before diving into any manual work: "Fix the TypeScript error in the user onboarding flow validation" "Update the webhooks endpoint to handle the new event schema" "Add better error boundaries to the admin dashboard React components" "Migrate the legacy auth middleware to use our new session management" These are the kinds of established codebase tasks that used to eat up 30-40% of my morning. Now Codex handles them while I grab coffee. The success rate has jumped from around 40-60% to what feels like 85-90% for well-scoped maintenance work. [...] For my portfolio site, I can now ask Codex to: "Add a new blog post template for interview posts with structured metadata" "Create a reading progress indicator component that matches the existing design system" "Implement tag-based filtering for the blog index page" It understands the existing Next.js structur