正在加载视频...

视频加载失败

返回首页

💥NEW: CODEX POWER USER GUIDE 3 rules that Codex power users follow to build better and get more done. Rule 1: The Verify Rule - Give Codex a way to verify its own work using browser use, computer use, and tests (and TDD). - Frame your prompts as a...

avthar's profile picture

Avthar Sewrathan

7,902 subscribers

113,667 次观看 • 2 个月前 •via X (Twitter)

科学技术教育
LIVE

Anya Rossi• Live Now

Private livecam show

1 条评论

Gabriel Turicianu 的头像
Gabriel Turicianu2 个月前

@avthar , actually you're current post and video helps somebody from this planet. I only wanted to let you know.

相关视频

I've unlocked 10x more from Codex since I've let the agent prompt and manage itself. I call this "The Orchestrator Rule". Here's why it works so well: - Models like GPT 5.6 Sol are getting better at inferring your intent. - Codex has the ability to create, monitor, and send messages to other Codex threads. - So you can just tell Codex the outcome you want, and Codex can turn that into detailed prompts, spin up one or more threads to do the work, and bring the results back to you. This changed my job as a builder: Instead of writing perfect prompts, I described outcomes with success criteria and verification methods. And Codex wrote the prompts and orchestrated the work for me. Hence the "Orchestrator" Rule. Here are 2 ways to let Codex prompt and manage itself: (1) Ask Codex to kick off a task in a new thread. - You can give it a short description of the outcome you want to achieve, and Codex will expand that into the detailed instructions it needs to deliver. (2) Keep one parent thread for each project and let Codex spin up new child threads for individual tasks - This pairs really well with Voice mode. - You can talk to your parent thread like a chief of staff. It can kick off the work using child threads and report back when it needs your input or when the task is complete. I demo both these methods below:
0:53

I've unlocked 10x more from Codex since I've let the agent prompt and manage itself. I call this "The Orchestrator Rule". Here's why it works so well: - Models like GPT 5.6 Sol are getting better at inferring your intent. - Codex has the ability to create, monitor, and send messages to other Codex threads. - So you can just tell Codex the outcome you want, and Codex can turn that into detailed prompts, spin up one or more threads to do the work, and bring the results back to you. This changed my job as a builder: Instead of writing perfect prompts, I described outcomes with success criteria and verification methods. And Codex wrote the prompts and orchestrated the work for me. Hence the "Orchestrator" Rule. Here are 2 ways to let Codex prompt and manage itself: (1) Ask Codex to kick off a task in a new thread. - You can give it a short description of the outcome you want to achieve, and Codex will expand that into the detailed instructions it needs to deliver. (2) Keep one parent thread for each project and let Codex spin up new child threads for individual tasks - This pairs really well with Voice mode. - You can talk to your parent thread like a chief of staff. It can kick off the work using child threads and report back when it needs your input or when the task is complete. I demo both these methods below:

Avthar Sewrathan

62,928 次观看 • 2 个月前

I use subagents for ~80% of my Codex tasks these days. If you're new to subagents, here's a quick primer: - Subagents = separate agents that work on a specific piece of work in a fresh isolated context window. - Your main thread can create subagents and delegate work to them. - Subagents report back when tasks are complete. - Codex subagents are especially useful for read-heavy tasks (e.g research, investigation, and review). - Also useful for testing and building parts of a project in parallel. Subagents are great for working on focused parts of a big task, like planning, implementation, testing, or review. My biggest pro tip for using subagents in Codex: You don’t have to design the entire delegation plan yourself. Just ask Codex to “Use subagents as needed,” and then Codex can then decide where subagents would help it in the task. Here's a demo of using subagents in Codex:
0:42

I use subagents for ~80% of my Codex tasks these days. If you're new to subagents, here's a quick primer: - Subagents = separate agents that work on a specific piece of work in a fresh isolated context window. - Your main thread can create subagents and delegate work to them. - Subagents report back when tasks are complete. - Codex subagents are especially useful for read-heavy tasks (e.g research, investigation, and review). - Also useful for testing and building parts of a project in parallel. Subagents are great for working on focused parts of a big task, like planning, implementation, testing, or review. My biggest pro tip for using subagents in Codex: You don’t have to design the entire delegation plan yourself. Just ask Codex to “Use subagents as needed,” and then Codex can then decide where subagents would help it in the task. Here's a demo of using subagents in Codex:

Avthar

18,444 次观看 • 2 个月前

ChatGPT Voice is now available on Desktop in Work and Codex! And your Codex Micro is already fully compatible with it. It's never been easier to talk to your computer, launch and manage Codex tasks, and basically do anything with Codex. A truly feel AGI moment to me.
0:42

ChatGPT Voice is now available on Desktop in Work and Codex! And your Codex Micro is already fully compatible with it. It's never been easier to talk to your computer, launch and manage Codex tasks, and basically do anything with Codex. A truly feel AGI moment to me.

Thomas Ricouard

20,192 次观看 • 3 个月前

Today, we launched browser use inside Codex to further close the build & verify loop for local development! Now, you can ask Codex to build your front end, and test it like a user would by clicking through the app. Codex sees everything a user sees through vision & checks the network/console logs to help debug & fix any issues that it finds. This change brings us closer to fully autonomous coding agents that delivers high quality and tested changes. Watch Codex test my app in the browser, catch & fix a real bug, and doing that loop again with a brand new feature.
0:37

Today, we launched browser use inside Codex to further close the build & verify loop for local development! Now, you can ask Codex to build your front end, and test it like a user would by clicking through the app. Codex sees everything a user sees through vision & checks the network/console logs to help debug & fix any issues that it finds. This change brings us closer to fully autonomous coding agents that delivers high quality and tested changes. Watch Codex test my app in the browser, catch & fix a real bug, and doing that loop again with a brand new feature.

James Sun

227,571 次观看 • 6 个月前

I built a new plugin! You can now trigger Codex from Claude Code! Use the Codex plugin for Claude Code to delegate tasks to Codex or have Codex review your changes using your ChatGPT subscription. Start by installing the plugin:
0:39

I built a new plugin! You can now trigger Codex from Claude Code! Use the Codex plugin for Claude Code to delegate tasks to Codex or have Codex review your changes using your ChatGPT subscription. Start by installing the plugin:

dominik kundel

1,292,706 次观看 • 7 个月前

Delegate work in Codex to your dot. Your dot can now start work in Codex and follow up on existing threads, drawing on your ChatGPT conversations, Codex threads, and automations. It’s also better at deciding when to keep a thread going or start fresh. Your dot can also review and edit Scheduled Tasks in ChatGPT Work, too. Ask what’s scheduled or update a recurring task as plans change.
0:24

Delegate work in Codex to your dot. Your dot can now start work in Codex and follow up on existing threads, drawing on your ChatGPT conversations, Codex threads, and automations. It’s also better at deciding when to keep a thread going or start fresh. Your dot can also review and edit Scheduled Tasks in ChatGPT Work, too. Ask what’s scheduled or update a recurring task as plans change.

ChatGPT

955,637 次观看 • 1 个月前

We’re adding support for WebMCP in the ChatGPT desktop app’s built-in browser and ChatGPT Sites. When you visit a compatible website, ChatGPT or Codex can automatically use it to complete your task. Update to the latest version of the ChatGPT desktop app, then just ask Codex to create a WebMCP-enabled app and deploy it to Sites.
2:16

We’re adding support for WebMCP in the ChatGPT desktop app’s built-in browser and ChatGPT Sites. When you visit a compatible website, ChatGPT or Codex can automatically use it to complete your task. Update to the latest version of the ChatGPT desktop app, then just ask Codex to create a WebMCP-enabled app and deploy it to Sites.

OpenAI Developers

379,206 次观看 • 2 个月前

🥅 /goal has graduated from an experiment—for tasks big and small, Codex gets your work done. Use goal mode in the Codex app, IDE Extension, or CLI to give Codex a specific milestone, and it will keep working until it gets there, even across hours or days. You can check in and steer, and even pause Codex along the way. Pro tip: start side chats to understand the work that has been done so far without having to interrupt the main task.
1:38

🥅 /goal has graduated from an experiment—for tasks big and small, Codex gets your work done. Use goal mode in the Codex app, IDE Extension, or CLI to give Codex a specific milestone, and it will keep working until it gets there, even across hours or days. You can check in and steer, and even pause Codex along the way. Pro tip: start side chats to understand the work that has been done so far without having to interrupt the main task.

OpenAI Developers

444,633 次观看 • 5 个月前

💡 Friday Codex tip: If you are using the Codex app and regularly find yourself copy and pasting text from error messages or plans from other apps into Codex to start a new task, you can use Raycast deeplinks to map it to a hotkey.
1:36

💡 Friday Codex tip: If you are using the Codex app and regularly find yourself copy and pasting text from error messages or plans from other apps into Codex to start a new task, you can use Raycast deeplinks to map it to a hotkey.

dominik kundel

92,469 次观看 • 8 个月前

7M+ weekly Codex users. 150+ updates in two months. Romain Huet catches you up on what’s new in Codex: GPT‑5.6 and Ultra Parallel work with /goal Faster computer use AppShots Inline edits Sites Codex mobile and SSH workflows PRs from review to merge
7:12

7M+ weekly Codex users. 150+ updates in two months. Romain Huet catches you up on what’s new in Codex: GPT‑5.6 and Ultra Parallel work with /goal Faster computer use AppShots Inline edits Sites Codex mobile and SSH workflows PRs from review to merge

OpenAI Developers

296,199 次观看 • 4 个月前

yesterday, at the Codex hackathon, i ended up solving this problem by building an MCP connector app that turns ChatGPT into Codex, sort of. 1. you get to use GPT-5.5 Pro by exposing your local dev environment to ChatGPT, so you can use 5.5 pro for planning and handover to codex to execute it 2. you get to 2x your rate limits, just like last month, because apparently ChatGPT and Codex have separate rate limits here is the quick demo
0:27

yesterday, at the Codex hackathon, i ended up solving this problem by building an MCP connector app that turns ChatGPT into Codex, sort of. 1. you get to use GPT-5.5 Pro by exposing your local dev environment to ChatGPT, so you can use 5.5 pro for planning and handover to codex to execute it 2. you get to 2x your rate limits, just like last month, because apparently ChatGPT and Codex have separate rate limits here is the quick demo

waishnav

558,895 次观看 • 5 个月前

With the Codex app you can: - Multitask effortlessly: Work with multiple agents in parallel and keep agent changes isolated with worktrees - Create & use skills: package your tools + conventions into reusable capabilities ⁃ Set up automations: delegate repetitive work to Codex with scheduled workflows in the background
2:12

With the Codex app you can: - Multitask effortlessly: Work with multiple agents in parallel and keep agent changes isolated with worktrees - Create & use skills: package your tools + conventions into reusable capabilities ⁃ Set up automations: delegate repetitive work to Codex with scheduled workflows in the background

OpenAI

396,730 次观看 • 9 个月前

How to use Open Design inside Codex: Ask Codex to deploy Open Design locally, then tell Codex what you want to build. The real unlock: Codex can operate the design tool for you — choosing workflows, filling briefs, inspecting files, testing interactions, and iterating on the result. Design tools are becoming agent-operated.
0:48

How to use Open Design inside Codex: Ask Codex to deploy Open Design locally, then tell Codex what you want to build. The real unlock: Codex can operate the design tool for you — choosing workflows, filling briefs, inspecting files, testing interactions, and iterating on the result. Design tools are becoming agent-operated.

OpenDesign

133,420 次观看 • 5 个月前

codex computer use uses secret macos api it makes codex to work while you work with your computer, no need to use virtualized machine but that secret macos api is no longer a secret cuz i found it and re implemented it as an mcp lmao
2:39

codex computer use uses secret macos api it makes codex to work while you work with your computer, no need to use virtualized machine but that secret macos api is no longer a secret cuz i found it and re implemented it as an mcp lmao

Q

50,866 次观看 • 3 个月前

"You cannot walk from point A to B inside OpenAI without hearing Codex get mentioned." Here's my new episode with Rohan Varma (Codex PM) on how he uses Codex as his everything app to: → Prototype designs with Image Gen → Turn repeated work into automations → Turn project context into live Codex Sites → Use one Codex thread to manage others Some quotes from Rohan: "[Ask Codex] for something that seems 10x more ridiculous than you ever think it could do. And it probably can do 90% of it." "Over the course of the day, I'm probably doing 3-4x more than I would have without Codex." "For me, every time I do anything I basically think, could Codex have done this?" 📌 Watch now: Thanks to our sponsors: Wispr Flow: 4x faster than typing with your voice Riverside: All-in-one AI studio for podcasts and video
0:29

"You cannot walk from point A to B inside OpenAI without hearing Codex get mentioned." Here's my new episode with Rohan Varma (Codex PM) on how he uses Codex as his everything app to: → Prototype designs with Image Gen → Turn repeated work into automations → Turn project context into live Codex Sites → Use one Codex thread to manage others Some quotes from Rohan: "[Ask Codex] for something that seems 10x more ridiculous than you ever think it could do. And it probably can do 90% of it." "Over the course of the day, I'm probably doing 3-4x more than I would have without Codex." "For me, every time I do anything I basically think, could Codex have done this?" 📌 Watch now: Thanks to our sponsors: Wispr Flow: 4x faster than typing with your voice Riverside: All-in-one AI studio for podcasts and video

Peter Yang

141,909 次观看 • 4 个月前

You can now prompt Codex to spin up new threads inside Codex.
0:23

You can now prompt Codex to spin up new threads inside Codex.

Riley Brown

127,114 次观看 • 5 个月前

Still wondering how you can use Codex for (almost) everything? Codex can help with more of the work that supports the work, from organizing research to making spreadsheets, decks, and summaries.
0:38

Still wondering how you can use Codex for (almost) everything? Codex can help with more of the work that supports the work, from organizing research to making spreadsheets, decks, and summaries.

OpenAI

387,472 次观看 • 6 个月前

Codex can now take on more of your browser dev work. With the new Chrome plugin in the Codex app, it can test web apps, gather context across tabs, use web DevTools efficiently in parallel, and keep results organized without taking over your browser.
2:34

Codex can now take on more of your browser dev work. With the new Chrome plugin in the Codex app, it can test web apps, gather context across tabs, use web DevTools efficiently in parallel, and keep results organized without taking over your browser.

OpenAI Developers

231,655 次观看 • 6 个月前

Introducing developer mode for browser use in Chrome and the Codex in-app browser. Codex can use the Chrome DevTools Protocol (CDP) to debug browser issues by profiling JavaScript performance and inspecting console output, network traffic, and page state.
1:27

Introducing developer mode for browser use in Chrome and the Codex in-app browser. Codex can use the Chrome DevTools Protocol (CDP) to debug browser issues by profiling JavaScript performance and inspecting console output, network traffic, and page state.

OpenAI Developers

378,245 次观看 • 5 个月前

Codex has come a long way since April. Over the next two weeks, we’re releasing a series of videos to help you get better acquainted with Codex — starting with how to use the Codex CLI with GPT-5-Codex.
5:42

Codex has come a long way since April. Over the next two weeks, we’re releasing a series of videos to help you get better acquainted with Codex — starting with how to use the Codex CLI with GPT-5-Codex.

OpenAI Developers

190,153 次观看 • 1 年前