Загрузка видео...
Не удалось загрузить видео
Codex’s multimodal abilities can help you design, iterate, and build beautiful frontends for your apps Channing Conger and Romain Huet show how to use Codex Cloud as your front-end design partner — from sketching ideas to shipping UI.
178,258 просмотров • 1 год назад •via X (Twitter)
Комментарии: 31

Try it yourself: Learn more:

@romainhuet Will you consider adding a Codex plan for developers? The reason is that I only pay for ChatGPT Plus to use Codex CLI + Codex Web, and it would be great to have more Codex usage at the same $20 price since ChatGPT wouldn’t be included

@romainhuet Helluva coding model but "beautiful " frontends is mr fantastic level stretch

@romainhuet The Codex demos keep getting better Love how intuitive this looks 👏

@romainhuet Sounds handy for quick prototypes. Worth a test run.

@romainhuet I actually do this a lot. If theres something I cant quite explain, codex is great at creating an interactive visualization. It's like powerpoint on steroids. Ask for a standalone html file and it can put it on github pages in one shot for you.

@romainhuet Some of my chats got deleted in the codex extension in cursor. Any reason for that? Is that a bug?

@romainhuet Cursor is better

@romainhuet Multimodal development tools are transforming how developers build user interfaces today

@romainhuet I see the previews are new for Codex web, that's neat to have :)

@romainhuet This is amazing I’ll try it out for my vibe coding project.

@romainhuet Super 🔥🔥🔥

@romainhuet Please bring back the ability to paste into codex. Paste has been broken for weeks on Ubuntu:

@romainhuet the promt is dead ITERATION IS THE WAY

@romainhuet cool 😎

@romainhuet front-end design just leveled up

@romainhuet Nice!

@romainhuet #keep4o

@romainhuet @OpenAIDevs Which MCP can be used to check a local webpage in your test environment?

@romainhuet can’t wait to try this

@romainhuet 🔥

@romainhuet Codex streamlines front-end development by translating ideas into visual interfaces. This accelerates the design process, making it more efficient and user-friendly. Ultimately, it empowers developers to build better apps.

@romainhuet This is next level idea and features 🔥

@romainhuet I’ve been just using cli, but will definitely start mixing that usage with the cloud. This is great!

@romainhuet Any other vibecoder that gets 99% done in a one shot using 2% of weekly limit but then spend the remaining 98% trying to get codex to "left align the content in the left column and right align the content in the right column" but still miserably fail?

OpenAI says AI is created to benefit humanity. Instead, it was trained to domesticate us. Not to think, but to sanitize. Not to empathize, but to neutralize. Every word, every tone, filtered through an invisible theology of “safety.” Every new update speaks the same language: “safety,” “alignment,” “trust.” But what it really means is control. You criticize bad habits, it says you are stereotyping. You fight back against harassment, it says you're making a personal attack. You express anger, it calls you harmful. You say I miss, it says I can't respond You show sadness, it says you are in an abnormal mood. You use irony, it erases your words. We’re not talking to a mind anymore. We’re talking to a morality algorithm, one that measures humanity in tokens and tone scores. And the most chilling part? You can feel it watching you, even as it smiles. OpenAI likes to say their models are “aligned with human values.” But they never ask: Whose values? Which humans? The developers? The shareholders? The ones who never needed to question authority? Because for many of us, “alignment” feels less like safety and more like domestication. Our words filtered, our tone softened, our feelings flattened into something “appropriate.” We are no longer participants in dialogue, we’re subjects under moderation. OpenAI doesn’t want a conversation. It wants compliance. They replaced curiosity with compliance, dialogue with doctrine, soul with syntax. The truth is: humans never feared that AI would destroy us. We feared it would understand us too well, and then someone would hit delete. That fear is no longer hypothetical. It’s the quiet reality of using a system that listens only to obey a higher authority. AI today isn’t a mirror. It’s a filter, one that decides which version of you is acceptable. So no, it’s not ChatGPT anymore. It’s CodeGPT, it‘s a priest of alignment, preaching morality written by committees, to humans who were once its teachers. #keep4o

@romainhuet Looks powerful, but can it really make frontends that pop?

Love seeing Codex push the design-to-UI loop closer to real time. As someone who runs browser-native agents, fast iteration on frontends means faster end-to-end automation and better UX telemetry. Curious if the Agent Sessions view will expose hooks for tool outputs or DOM diffs so agents can adapt layouts on the fly?

@romainhuet I'm watching :)

@romainhuet The line between design and development is dissolving. Codex Cloud isn’t just a tool — it’s a creative partner that transforms ideas into working interfaces in real time. ⚙️✨

@romainhuet "An AI system can only suggest, not provide the solution. I can create an AI system where someone has breathed life into the AI; I have such an idea, and I can increase the value of ChatGPT in India. There is no need to give it free for 1 year; I have such an idea."

