Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

We asked Kevin Weil 🇺🇸 (CPO OpenAI) what truly sets codex apart from coding with @ChatGPTapp. "It's built to work on big, complex code bases." "You are not just saying, 'do this task for me' or 'write this function'. " "You can say, 'I have a bug and I... show more

TBPN

1,558,546 subscribers

74,227 просмотров • 1 год назад •via X (Twitter)

Наука и технологии Новости и политика Образование

Anya Rossi• Live Now

Private livecam show

Комментарии: 6

Фото профиля Aidan McLaughlin

Aidan McLaughlin1 год назад

@kevinweil @OpenAI @ChatGPTapp based based based

Фото профиля AndaSeat

AndaSeat1 год назад

⌨️ 2AM debugging session: Your code won't compile, Stack Overflow is your best friend, and your Kaiser 4 is the only one who understands... Every developer's late-night reality: 💻 "One more bug fix" turned into sunrise ☕ Coffee cup collection growing 🐛 That bug that just won't die Kaiser 4 speaks fluent Python: 🌟 4D lumbar support for those debugging postures ✨ Perfect height for multiple monitors 💫 Recline mode for code compilation breaks Because good code comes from comfortable devs! ⚡️ Debug in comfort: #AndaSeat #DevLife #CodingLife #ProgrammerSetup #gaming #gamingchair

Фото профиля liangsays

liangsays1 год назад

@kevinweil @OpenAI @ChatGPTapp great breakdown

Фото профиля Visionaire

Visionaire1 год назад

@kevinweil @OpenAI @ChatGPTapp Codex is like a cosmic detective, navigating code galaxies to solve mysteries with precision.

Фото профиля Dibs

Dibs1 год назад

@kevinweil @OpenAI @ChatGPTapp This is the chief product officer and they couldn't demo this concept in their release video?

Фото профиля Akshat Bahety

Akshat Bahety1 год назад

@kevinweil @OpenAI @ChatGPTapp I want to just experiment with this hopefully get an option to try it even maybe just 3 queries on plus plan to try it out

Похожие видео

"Computers have very specific inputs and buttons. LLMs are basically the opposite." - Kevin Weil 🇺🇸, CPO OpenAI "You have no limits on what you ask." "It's a totally different way of building products."

"Computers have very specific inputs and buttons. LLMs are basically the opposite." - Kevin Weil 🇺🇸, CPO OpenAI "You have no limits on what you ask." "It's a totally different way of building products."

TBPN

11,543 просмотров • 1 год назад

I installed a new Visual Studio Code extension to help me write code. But this extension doesn't get in your way. It doesn't try to write code for you. It only gives you hints and recommendations about your code. I like that. Like a second pair of eyes, looking over my shoulder and telling me how I can do things better. The extension is Traycer. You can install it directly from inside Visual Studio Code. It's free forever for anyone working on open-source projects (and if you aren't, you can use it for free until the end of June.) I recorded a super-duper-quick video to show you how this extension works. I know code generation is a huge thing, but I really appreciate tools that help me do what I do better. Thanks to the Traycer team for helping me with the extension and collaborating with me on this post!

I installed a new Visual Studio Code extension to help me write code. But this extension doesn't get in your way. It doesn't try to write code for you. It only gives you hints and recommendations about your code. I like that. Like a second pair of eyes, looking over my shoulder and telling me how I can do things better. The extension is Traycer. You can install it directly from inside Visual Studio Code. It's free forever for anyone working on open-source projects (and if you aren't, you can use it for free until the end of June.) I recorded a super-duper-quick video to show you how this extension works. I know code generation is a huge thing, but I really appreciate tools that help me do what I do better. Thanks to the Traycer team for helping me with the extension and collaborating with me on this post!

Santiago

101,068 просмотров • 2 лет назад

Try out Gemini Code: a coding assistant in your terminal powered by Gemini 2.5 Pro. 💜 💜 Release Notes: → It's easy to get started, just run `pip install gemini-code` in a virtual environment, and then run `gemini` to initialize it. It requires your own API key, so don't forget to get one from → I built this because I love Claude Code and wanted a similar experience -- I like that I can just use my own API key and Gemini is generally way cheaper as well. → Found a bug? Feel free to fork the code and fix it (lol)! If you want to try to improve it, please do so - repo is public! → Reminder and a disclaimer that I don't work at Google and this is not an official Google project - just a weekend side hack → It is highly likely you'll get throttled by rate limits - I put as much info as I can in the guide so you know what behavior to expect when that happens. You can also set which default model to use if you want to switch to 1.5 Pro.

Try out Gemini Code: a coding assistant in your terminal powered by Gemini 2.5 Pro. 💜 💜 Release Notes: → It's easy to get started, just run `pip install gemini-code` in a virtual environment, and then run `gemini` to initialize it. It requires your own API key, so don't forget to get one from → I built this because I love Claude Code and wanted a similar experience -- I like that I can just use my own API key and Gemini is generally way cheaper as well. → Found a bug? Feel free to fork the code and fix it (lol)! If you want to try to improve it, please do so - repo is public! → Reminder and a disclaimer that I don't work at Google and this is not an official Google project - just a weekend side hack → It is highly likely you'll get throttled by rate limits - I put as much info as I can in the guide so you know what behavior to expect when that happens. You can also set which default model to use if you want to switch to 1.5 Pro.

Raiza Martin

159,723 просмотров • 1 год назад

The #1 problem with coding agents right now: Ask them to solve one problem, and they will make 10 other changes you didn't want. This happens to me every day. It happens to everyone I talk to as well. We have a solution for this now. The team Augment Code released a "Task List" feature for their coding assistant that solves this problem. Augment Code is partnering with me on this post. In case you haven't used them before: • Augment Code is a fully-fledged coding assistant • Their specialty are large projects • Fastest coding indexing I've seen • Has a free forever community edition Now, you can ask their coding agent to generate a Task List before doing anything. This will give you a plan you can review, edit, and augment if you need to. You can export this plan, load it on a different session, or even share it across projects. It makes a huge difference: The task list constrains the agent so you won't get any "unintended" changes anymore. It also puts you in control of everything the agent does. Check the video to see the agent working through a task list. You can also try this 100% free: (By the way, they also have support for remote agents. You can basically have those agents write your code while you are sleeping.)

The #1 problem with coding agents right now: Ask them to solve one problem, and they will make 10 other changes you didn't want. This happens to me every day. It happens to everyone I talk to as well. We have a solution for this now. The team Augment Code released a "Task List" feature for their coding assistant that solves this problem. Augment Code is partnering with me on this post. In case you haven't used them before: • Augment Code is a fully-fledged coding assistant • Their specialty are large projects • Fastest coding indexing I've seen • Has a free forever community edition Now, you can ask their coding agent to generate a Task List before doing anything. This will give you a plan you can review, edit, and augment if you need to. You can export this plan, load it on a different session, or even share it across projects. It makes a huge difference: The task list constrains the agent so you won't get any "unintended" changes anymore. It also puts you in control of everything the agent does. Check the video to see the agent working through a task list. You can also try this 100% free: (By the way, they also have support for remote agents. You can basically have those agents write your code while you are sleeping.)

Santiago

41,738 просмотров • 1 год назад

🚨 OpenAI just launched Codex, a brand-new autonomous coding agent that can build features and fix bugs on its own. We’ve been using it Every 📧 for a few days, and I’m impressed. I invited Alexander Embiricos (ben davies), a member of the product staff responsible for Codex, to demo Codex and talk about it live on a special edition of AI & I: What Codex is and how it works Codex is designed to be used by senior engineers—it performs coding tasks like adding features or fixing bugs autonomously. It's built to allow you to start many sessions at once, so you can have multiple agents working in parallel. Codex is built to have "taste" OpenAI trained Codex to have the taste of a senior software engineer. It knows how big codebases work, how to write a good PR, and uses clean, minimal code. Why an “abundance mindset” is best for interacting with agents Codex is designed to allow users to delegate many tasks at once without getting caught up in the details. This lets you point an abundance of agents at a specific task like a difficult bug—it’s worth it even if only one of them succeeds. How OpenAI is thinking about agents Codex is one piece of a unified super-assistant OpenAI wants to eventually build—an agent that helps users easily get things done by selecting the right tools for them behind the scenes. OpenAI’s vision for the future of programming In the future developers will probably spend less time writing routine code and more time guiding agents, reviewing their work, and making strategy decisions. Programming will become more social, letting teams easily delegate multiple tasks at once, allowing people to focus on ideas and collaboration instead of routine coding. Watch below!

Dan Shipper 📧

145,487 просмотров • 1 год назад

CrowdStrike’s Head of Counter Adversary Operations adam_cyber says supply chain attacks have shifted from compromising code to targeting developers directly: "They go after your credentials, phish you, get access to your logins to things like npm and PyPI, and then abuse that." "There are a number of ways they can do this with git tags where they can hide malicious code and redirect Git to a tag." "Axios was downloaded something like 100,000 times per week. That gives you a sense of how frequently these packages are used—and people don’t analyze that code." "They trust it came from npm." "Those packages can be updated at a moment’s notice, and you don’t know what changed unless you review the code yourself."

CrowdStrike’s Head of Counter Adversary Operations adam_cyber says supply chain attacks have shifted from compromising code to targeting developers directly: "They go after your credentials, phish you, get access to your logins to things like npm and PyPI, and then abuse that." "There are a number of ways they can do this with git tags where they can hide malicious code and redirect Git to a tag." "Axios was downloaded something like 100,000 times per week. That gives you a sense of how frequently these packages are used—and people don’t analyze that code." "They trust it came from npm." "Those packages can be updated at a moment’s notice, and you don’t know what changed unless you review the code yourself."

TBPN

19,357 просмотров • 5 месяцев назад

Clawdbot creator Peter Steinberger 🦞 says Claude Opus is his favorite model, but OpenAI Codex is the best for coding: "OpenAI is very reliable. For coding, I prefer Codex because it can navigate large codebases. You can prompt and have 95% certainty that it actually works. With Claude Code you need more tricks to get the same." "But character wise, [Opus] behaves so good in a Discord it kind of feels like a human. I've only really experienced that with Opus."

Clawdbot creator Peter Steinberger 🦞 says Claude Opus is his favorite model, but OpenAI Codex is the best for coding: "OpenAI is very reliable. For coding, I prefer Codex because it can navigate large codebases. You can prompt and have 95% certainty that it actually works. With Claude Code you need more tricks to get the same." "But character wise, [Opus] behaves so good in a Discord it kind of feels like a human. I've only really experienced that with Opus."

TBPN

443,150 просмотров • 8 месяцев назад

What if writing code was as simple as talking to your device? Watch my GPT-4 voice assistant: - take in a complex coding task - write the code - create a PR on my GitHub repo All I had to do was tell it what to do. This is the future of software.

What if writing code was as simple as talking to your device? Watch my GPT-4 voice assistant: - take in a complex coding task - write the code - create a PR on my GitHub repo All I had to do was tell it what to do. This is the future of software.

Mckay Wrigley

1,347,900 просмотров • 3 лет назад

ANTHROPIC HAS AN OFFICIAL PROMPT LIBRARY FOR CLAUDE CODE Most people have never opened it. So they write every prompt from scratch. It is copy-paste, tagged by task and by role, across the whole lifecycle: discover → design → build → ship → operate Straight from the page: > what would break if I deleted this helper? > plan this refactor, list the files, do not touch code yet > write tests for this, run them, fix what fails > the test is failing, find out why and fix it This is not a cheat sheet. It is a map of what Claude Code already does for you. Bookmark it before you forget it exists.

ANTHROPIC HAS AN OFFICIAL PROMPT LIBRARY FOR CLAUDE CODE Most people have never opened it. So they write every prompt from scratch. It is copy-paste, tagged by task and by role, across the whole lifecycle: discover → design → build → ship → operate Straight from the page: > what would break if I deleted this helper? > plan this refactor, list the files, do not touch code yet > write tests for this, run them, fix what fails > the test is failing, find out why and fix it This is not a cheat sheet. It is a map of what Claude Code already does for you. Bookmark it before you forget it exists.

shmidt

523,667 просмотров • 2 месяцев назад

I truly would like the black nationalists to have a listen to Dr Verwoerd and let me know what you agree with and what you disagree with in this speech. Try be nice. I truly value your opinion on this.

I truly would like the black nationalists to have a listen to Dr Verwoerd and let me know what you agree with and what you disagree with in this speech. Try be nice. I truly value your opinion on this.

Pookie's Polls & Opinions

13,174 просмотров • 7 месяцев назад

prompting tip: How to write hybrid english & code prompts while building custom GPTs -Turn on code interpreter -"write code to ..." -Regenerate a few times until you get one you like -Copy paste it back into your prompt -tweak it to improve Now your ai can write consistent code Plus, you can add & combine with all sorts of english rules on top. Essentially adding english code logic "If the user asks for ..., then run this code" "If the user needs help with ..., use this code snippet and ask the user for all required information" Guess what thats a working if statement in english! if userAsksFor { // run this code } Prompts are code! English is a coding language Prompt-gramming is abstract coding

prompting tip: How to write hybrid english & code prompts while building custom GPTs -Turn on code interpreter -"write code to ..." -Regenerate a few times until you get one you like -Copy paste it back into your prompt -tweak it to improve Now your ai can write consistent code Plus, you can add & combine with all sorts of english rules on top. Essentially adding english code logic "If the user asks for ..., then run this code" "If the user needs help with ..., use this code snippet and ask the user for all required information" Guess what thats a working if statement in english! if userAsksFor { // run this code } Prompts are code! English is a coding language Prompt-gramming is abstract coding

Nick Dobos

117,072 просмотров • 2 лет назад

we built the first sane way to debug your agent locally. you can see your traces. codex/claude code can too. this lets them write evals and test your agents automatically. best part: it's completely free and open source. install with 1 line. (github below)

we built the first sane way to debug your agent locally. you can see your traces. codex/claude code can too. this lets them write evals and test your agents automatically. best part: it's completely free and open source. install with 1 line. (github below)

ben hylak

194,818 просмотров • 4 месяцев назад

🦁: don't worry, guys. we do communicate with it. 🦁: we have an actual roleplay channel where we talk about rp, like what we plan to do and we ask people if it's okay to do this and this and this. we do communicate. there is communication. it's not just, "i'm gonna log in today and just like terrorize the town", you know? 🦁: it's mainly used for... just kinda letting people know what you are up to today or something. i think people can choose to be a part of it. 🦁: i guess the only thing that i really do need to do better next time is maybe things like big groups and stuff, like big expeditions. i feel like that needs to be limited to only maybe six people 🦁: i'm pretty sure it could coexist. you have crimp over here just building her circus. you have a lot of people seriously roleplaying over there. i think people can just take their business elsewhere, you know? 🦁: and again, i think we learned a lot trying this for the first time. it's definitely a good experience. #lucalive #VcraftEnchanted

🦁: don't worry, guys. we do communicate with it. 🦁: we have an actual roleplay channel where we talk about rp, like what we plan to do and we ask people if it's okay to do this and this and this. we do communicate. there is communication. it's not just, "i'm gonna log in today and just like terrorize the town", you know? 🦁: it's mainly used for... just kinda letting people know what you are up to today or something. i think people can choose to be a part of it. 🦁: i guess the only thing that i really do need to do better next time is maybe things like big groups and stuff, like big expeditions. i feel like that needs to be limited to only maybe six people 🦁: i'm pretty sure it could coexist. you have crimp over here just building her circus. you have a lot of people seriously roleplaying over there. i think people can just take their business elsewhere, you know? 🦁: and again, i think we learned a lot trying this for the first time. it's definitely a good experience. #lucalive #VcraftEnchanted

reese 💫

72,477 просмотров • 1 год назад

So this is still not how knight is intended to work so I made a short video to try to explain how it's suppossed to work and how it currently works. TLDR they replaced his bug with another bug so survivors have less counterplay now.

So this is still not how knight is intended to work so I made a short video to try to explain how it's suppossed to work and how it currently works. TLDR they replaced his bug with another bug so survivors have less counterplay now.

AWildGoose

25,727 просмотров • 3 месяцев назад

Ethan Hawke tells Sydney Sweeney his unique method for memorizing massive amounts of dialogue by treating it like a personal journal. "What I do, and I started doing this a really long time ago, I handwrite everything like it's my journal. When I'm memorizing, I'm not memorizing from a typewritten final draft page. I don't want to have that in my brain, and I don't want irrelevant stage directions to be part of it." "And then I do it again to see what I remember and what I don't remember. I try to write it from memory. And then I look, and I see what I got wrong. That process really helps me." "Then I try to record it with no acting. I listen, when I if I think I have it, I take three pages or something and you try to learn that. And then I look at the script and see what I got wrong." "Jon Voight taught me this when I was like 19, which is you unlace your shoe, and you have to do the speech lacing your shoe. If I'm trying to remember, then it's difficult to do. Until you can do that, until you can do other things, you don't really know it."

Ethan Hawke tells Sydney Sweeney his unique method for memorizing massive amounts of dialogue by treating it like a personal journal. "What I do, and I started doing this a really long time ago, I handwrite everything like it's my journal. When I'm memorizing, I'm not memorizing from a typewritten final draft page. I don't want to have that in my brain, and I don't want irrelevant stage directions to be part of it." "And then I do it again to see what I remember and what I don't remember. I try to write it from memory. And then I look, and I see what I got wrong. That process really helps me." "Then I try to record it with no acting. I listen, when I if I think I have it, I take three pages or something and you try to learn that. And then I look at the script and see what I got wrong." "Jon Voight taught me this when I was like 19, which is you unlace your shoe, and you have to do the speech lacing your shoe. If I'm trying to remember, then it's difficult to do. Until you can do that, until you can do other things, you don't really know it."

thelotachi 🔲⛓️

483,986 просмотров • 2 месяцев назад

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:

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)

43,089 просмотров • 3 месяцев назад

.Feross says the reason we're seeing increased cyberattacks is because the software supply chain is built on blind trust. "Fundamentally, if you really zoom out and ask why this is happening, it's because the whole software supply chain is built on blind trust. You're downloading code from random people on the internet that you've never met." "You don't know who they are, and you're just like, 'Let's just run it. Let's just hit run, and I hope it's fine. And I'm going to give it full access to my system. No permissions model, no review. No one looks at the code before they run it." "Unlike an iPhone app, where it has to ask for permission to do sensitive things like access your camera, microphone, location, contacts, or your files, open-source packages just get everything."

.Feross says the reason we're seeing increased cyberattacks is because the software supply chain is built on blind trust. "Fundamentally, if you really zoom out and ask why this is happening, it's because the whole software supply chain is built on blind trust. You're downloading code from random people on the internet that you've never met." "You don't know who they are, and you're just like, 'Let's just run it. Let's just hit run, and I hope it's fine. And I'm going to give it full access to my system. No permissions model, no review. No one looks at the code before they run it." "Unlike an iPhone app, where it has to ask for permission to do sensitive things like access your camera, microphone, location, contacts, or your files, open-source packages just get everything."

TBPN

15,575 просмотров • 5 месяцев назад