正在加载视频...

视频加载失败

返回首页

If you're using Codex, you're probably wasting tokens without realizing it. There's a Codex trick going viral right now that claims it can cut your token usage by up to 90%. Here's what most people do wrong. They open Codex and immediately say: “Build me an app.” So Codex...

dubibubiii's profile picture

Dubi

4,799 subscribers

20,200 次观看 • 2 个月前 •via TikTok

教育科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

I built a plugin for Codex so it can Create and Animate sprites for your game Install from inside codex app, connect your SpriteCook account, and tell it to what to create! Available here (experimental):
0:46

I built a plugin for Codex so it can Create and Animate sprites for your game Install from inside codex app, connect your SpriteCook account, and tell it to what to create! Available here (experimental):

Kimo

32,898 次观看 • 7 个月前

Runway Dev is now on Codex One plugin install gives Codex everything it needs to build Runway’s API into your app. Describe what your app should generate and let Codex build the integration autonomously. Get started at the link below.
0:52

Runway Dev is now on Codex One plugin install gives Codex everything it needs to build Runway’s API into your app. Describe what your app should generate and let Codex build the integration autonomously. Get started at the link below.

Runway

38,992 次观看 • 18 天前

Meet Codex CLI—an open-source local coding agent that turns natural language into working code. Tell Codex CLI what to build, fix, or explain, then watch it bring your ideas to life.
6:19

Meet Codex CLI—an open-source local coding agent that turns natural language into working code. Tell Codex CLI what to build, fix, or explain, then watch it bring your ideas to life.

OpenAI Developers

646,375 次观看 • 1 年前

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 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

1,292,765 次观看 • 7 个月前

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:
1:21

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:

Steve (Builder.io)

43,664 次观看 • 4 个月前

Codex is now a full video editor! Our new plugin opens a full built-in NLE right inside the Codex app, where you and your agent can edit together, effortlessly. If you're already paying for Codex, you get this one for FREE. It's available now. Start using it in 1 minute, by just telling your Codex: "Turn Codex into a Video Editor, read
1:04

Codex is now a full video editor! Our new plugin opens a full built-in NLE right inside the Codex app, where you and your agent can edit together, effortlessly. If you're already paying for Codex, you get this one for FREE. It's available now. Start using it in 1 minute, by just telling your Codex: "Turn Codex into a Video Editor, read

ChatCut

1,912,114 次观看 • 4 个月前

If you haven't set up Agents.md in Codex yet you can just copy the homework from Andrej Karpathy. Here's the exact setup (takes 2 minutes): 1. Go to his repo 2. Copy the 65-line Agents.md config 3. Paste it into Codex App → Global Custom Instructions 4. Done. You're already ahead of 90% of Codex users. It's minimalist. It's effective. Bookmark and Save it no matter. It'll be the most productive thing you will do this weekend
0:22

If you haven't set up Agents.md in Codex yet you can just copy the homework from Andrej Karpathy. Here's the exact setup (takes 2 minutes): 1. Go to his repo 2. Copy the 65-line Agents.md config 3. Paste it into Codex App → Global Custom Instructions 4. Done. You're already ahead of 90% of Codex users. It's minimalist. It's effective. Bookmark and Save it no matter. It'll be the most productive thing you will do this weekend

Avid

284,365 次观看 • 5 个月前

If you already use Claude Code or Codex and want to try Grok Bot, this is the fastest and easiest way I've found to set it up without rebuilding everything. The trick is making Grok Bot the execution layer while Claude Code or Codex does the actual work. It runs on the Anthropic and Codex plans you're already paying for and cuts your Grok Bot usage a ton. What I set up: - Opi, my operations manager bot. I logged it into Claude in its own browser and terminal, told it to run every task through Claude Code, and had it share that setup with the rest of the team - Tailscale, so my Mac Mini, MacBook Pro, iPhone and Grok Bot agent are all connected - Libby, a database librarian bot that went through my AI projects folder and catalogued every markdown file and skill, so the other bots know where everything lives Now Grok Bot can use everything I've already built with Claude Code and Codex, and all the bots work together.
2:50

If you already use Claude Code or Codex and want to try Grok Bot, this is the fastest and easiest way I've found to set it up without rebuilding everything. The trick is making Grok Bot the execution layer while Claude Code or Codex does the actual work. It runs on the Anthropic and Codex plans you're already paying for and cuts your Grok Bot usage a ton. What I set up: - Opi, my operations manager bot. I logged it into Claude in its own browser and terminal, told it to run every task through Claude Code, and had it share that setup with the rest of the team - Tailscale, so my Mac Mini, MacBook Pro, iPhone and Grok Bot agent are all connected - Libby, a database librarian bot that went through my AI projects folder and catalogued every markdown file and skill, so the other bots know where everything lives Now Grok Bot can use everything I've already built with Claude Code and Codex, and all the bots work together.

Mr. Paid Social

36,700 次观看 • 1 个月前

OpenAI took the best Coding model in the world GPT-5.3 Codex And turned it into a powerful coding app It's called Codex, but most people have no idea what you can build with it.
1:28:16

OpenAI took the best Coding model in the world GPT-5.3 Codex And turned it into a powerful coding app It's called Codex, but most people have no idea what you can build with it.

David Ondrej

24,923 次观看 • 9 个月前

Codex can now make launch videos. Introducing the Motion MCP for Codex Connect it to motion through the MCP, give it your assets and describe what you want. Codex builds the scenes, animations and transitions directly inside motion. This video was created using the MCP 👇
0:30

Codex can now make launch videos. Introducing the Motion MCP for Codex Connect it to motion through the MCP, give it your assets and describe what you want. Codex builds the scenes, animations and transitions directly inside motion. This video was created using the MCP 👇

Motion

94,973 次观看 • 2 个月前

💡 Codex Tip Create a local environment to have Codex auto install dependencies for your worktrees and create actions for quick access to common commands. Actions get executed in your integrated terminal so Codex can also access the terminal output. For iOS developers check out the iOS plugin that automatically sets up your actions to build and run your app!
1:02

💡 Codex Tip Create a local environment to have Codex auto install dependencies for your worktrees and create actions for quick access to common commands. Actions get executed in your integrated terminal so Codex can also access the terminal output. For iOS developers check out the iOS plugin that automatically sets up your actions to build and run your app!

dominik kundel

68,470 次观看 • 7 个月前

I love when Codex outsmarts me! Asked Codex to hack this badge that I got from Temporal's conference by putting Codex pets on it. I also gave it a photo of the badge along with it. Codex found the actual firmware of the badge on GitHub to have a starter 😂
0:23

I love when Codex outsmarts me! Asked Codex to hack this badge that I got from Temporal's conference by putting Codex pets on it. I also gave it a photo of the badge along with it. Codex found the actual firmware of the badge on GitHub to have a starter 😂

dominik kundel

35,125 次观看 • 6 个月前

💥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 goal (outcome + constraints + when to finish) instead of a task. - Require Codex to gather evidence (test outputs, screenshots, exit codes) to prove success. Rule 2: The Context Rule - Onboard Codex like you would a new employee or teammate. - Use Plugins to connect Codex to the tools and systems you use for development and knowledge work. - Create your own Agent Skills to encode business processes and workflows + make them legible to Codex. - Login to SaaS tools via Codex's in-app browser. - Combine plugins, browser use and skills with Scheduled Tasks to put meaningful work on autopilot. Rule 3: The Orchestrator Rule - Let Codex prompt and manage itself (Codex is better at prompting Codex than me or you). - Give Codex an outcome and ask it to spin up one or more threads to achieve it. - Use ChatGPT Voice Mode to talk to Codex like a chief of staff, have it spin up new threads to do work and report back with results. - Ask Codex to use subagents for planning, implementation and review. Any Codex tips or best practices I missed that you'd add? Watch my full full video guide (with examples and demos):
11:50

💥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 goal (outcome + constraints + when to finish) instead of a task. - Require Codex to gather evidence (test outputs, screenshots, exit codes) to prove success. Rule 2: The Context Rule - Onboard Codex like you would a new employee or teammate. - Use Plugins to connect Codex to the tools and systems you use for development and knowledge work. - Create your own Agent Skills to encode business processes and workflows + make them legible to Codex. - Login to SaaS tools via Codex's in-app browser. - Combine plugins, browser use and skills with Scheduled Tasks to put meaningful work on autopilot. Rule 3: The Orchestrator Rule - Let Codex prompt and manage itself (Codex is better at prompting Codex than me or you). - Give Codex an outcome and ask it to spin up one or more threads to achieve it. - Use ChatGPT Voice Mode to talk to Codex like a chief of staff, have it spin up new threads to do work and report back with results. - Ask Codex to use subagents for planning, implementation and review. Any Codex tips or best practices I missed that you'd add? Watch my full full video guide (with examples and demos):

Avthar Sewrathan

113,667 次观看 • 2 个月前

We use Codex to build our slides. Here's how. Douglas Brundage, used to spend hours formatting presentations. Now he gives Codex examples of what he wants and has it work directly in Google Slides. His workflow: 1. Make a few reference slides. Create an opening slide, a section break, and layouts for text or images. Show Codex the design you want it to repeat across the deck. 2. Decide what the slides should say. Settle the copy before asking Codex to build. Supply the images, too. For one presentation, Douglas pointed it to illustrations in Figma and asked it to place one on each section break. 3. Have Codex build the deck. It clicks, types, places images, and formats slides using your references. Review the result: In one deck, it crammed 30 examples onto a single slide. You can fix the slide yourself or tell it what to change. 4. Save the corrections for next time. Make your edits, then ask Codex to turn the reusable corrections into rules saved in your skills. The references give Codex a starting point. Your review catches what it misunderstood. Saving those corrections means the next deck will reflect more of your preferences from the outset. The full workflow:
0:24

We use Codex to build our slides. Here's how. Douglas Brundage, used to spend hours formatting presentations. Now he gives Codex examples of what he wants and has it work directly in Google Slides. His workflow: 1. Make a few reference slides. Create an opening slide, a section break, and layouts for text or images. Show Codex the design you want it to repeat across the deck. 2. Decide what the slides should say. Settle the copy before asking Codex to build. Supply the images, too. For one presentation, Douglas pointed it to illustrations in Figma and asked it to place one on each section break. 3. Have Codex build the deck. It clicks, types, places images, and formats slides using your references. Review the result: In one deck, it crammed 30 examples onto a single slide. You can fix the slide yourself or tell it what to change. 4. Save the corrections for next time. Make your edits, then ask Codex to turn the reusable corrections into rules saved in your skills. The references give Codex a starting point. Your review catches what it misunderstood. Saving those corrections means the next deck will reflect more of your preferences from the outset. The full workflow:

Every 📧

14,925 次观看 • 1 个月前

Wow very easy to create a Codex Site with a Convex DB that your agent can write to. You can make a todo list app that is hosted on Codex Sites, then tell Codex to make a skill that allows the agent to WRITE/EDIT to that todo list db. And then in any chat you can add to your list. Here's example.
0:40

Wow very easy to create a Codex Site with a Convex DB that your agent can write to. You can make a todo list app that is hosted on Codex Sites, then tell Codex to make a skill that allows the agent to WRITE/EDIT to that todo list db. And then in any chat you can add to your list. Here's example.

Riley Brown

54,081 次观看 • 5 个月前

We are bringing Codex Pets to the physical world Pick your pet, your hardware and bring them to life Connect to Codex desktop and never miss when the job finished Try it out and let me know what you think!
1:31

We are bringing Codex Pets to the physical world Pick your pet, your hardware and bring them to life Connect to Codex desktop and never miss when the job finished Try it out and let me know what you think!

Natalie

101,389 次观看 • 6 个月前

Introducing watchmen. It writes the skill files your coding agents should already have from your own sessions, shared across Claude Code, Codex, and pi, so you stop paying tokens to re-explain what your agent learned last week. Local and open-source.
0:26

Introducing watchmen. It writes the skill files your coding agents should already have from your own sessions, shared across Claude Code, Codex, and pi, so you stop paying tokens to re-explain what your agent learned last week. Local and open-source.

Dria

44,203 次观看 • 6 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