正在加载视频...

视频加载失败

返回首页

With all the buzz around the Codex App, OpenAI Developers quietly snuck out a new CLI update (0.94.0) as well. And boy is it an important update! Codex Plan mode is now officially released to the general audience! I am very excited about this one as it has a...

LLMJunky's profile picture

am.will

4,344 subscribers

57,121 次观看 • 6 个月前 •via X (Twitter)

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

ChatGPT Voice on desktop is the greatest plan mode I’ve ever used. I start with a blurry idea. It asks sharp questions that help me discover what I actually want, draws the architecture as we talk, then spins up a Codex task to build it.
0:50

ChatGPT Voice on desktop is the greatest plan mode I’ve ever used. I start with a blurry idea. It asks sharp questions that help me discover what I actually want, draws the architecture as we talk, then spins up a Codex task to build it.

Guinness Chen

70,330 次观看 • 12 天前

I never use planning mode in Codex. GPT 5.5 loves to research, so I just have a conversation and reach a pseudo-plan in chat. Then, I let it implement, maybe with a /fork beforehand to keep that plan as a revisit-able point. Probably the biggest switch coming from Claude Code
1:12

I never use planning mode in Codex. GPT 5.5 loves to research, so I just have a conversation and reach a pseudo-plan in chat. Then, I let it implement, maybe with a /fork beforehand to keep that plan as a revisit-able point. Probably the biggest switch coming from Claude Code

Ben Holmes

156,363 次观看 • 2 个月前

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."
1:47

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

443,022 次观看 • 6 个月前

Here's a short video (4m) that goes into more detail on how "vim mode" works in Ghostty and the multitude of features that are composed together to make it all work. This showcases how powerful Ghostty's keybinding system is getting! And don't worry, I plan on shipping a built-in "vim mode" table (unbound by default) so you can bind an opinionated "vim mode" with a single line in your config. But, if you want to modify it in any way, that's completely possible because this all works via standard config.
4:08

Here's a short video (4m) that goes into more detail on how "vim mode" works in Ghostty and the multitude of features that are composed together to make it all work. This showcases how powerful Ghostty's keybinding system is getting! And don't worry, I plan on shipping a built-in "vim mode" table (unbound by default) so you can bind an opinionated "vim mode" with a single line in your config. But, if you want to modify it in any way, that's completely possible because this all works via standard config.

Mitchell Hashimoto

87,819 次观看 • 7 个月前

The new GitHub Copilot Visual Studio Code Ask Questions tool is really cool - and has lot's of potential! As a start - real improvement for saving premium requests as the agent can halt mid-turn to ask the user questions - great for the built-in plan mode Try now in Insiders
0:29

The new GitHub Copilot Visual Studio Code Ask Questions tool is really cool - and has lot's of potential! As a start - real improvement for saving premium requests as the agent can halt mid-turn to ask the user questions - great for the built-in plan mode Try now in Insiders

Oren Melamed

15,277 次观看 • 6 个月前

So Alibaba has just released a coding plan with all the best open source models You’ve access to Qwen 3.5-Plus, Kimi K2.5, MiniMax M2.5, GLM-5, etc. And you can plug it to: - Claude Code (as I did) - OpenClaw - Codex - Cline… While being waaay cheaper than the paid plan of Codex, Claude & Cie. More below
0:36

So Alibaba has just released a coding plan with all the best open source models You’ve access to Qwen 3.5-Plus, Kimi K2.5, MiniMax M2.5, GLM-5, etc. And you can plug it to: - Claude Code (as I did) - OpenClaw - Codex - Cline… While being waaay cheaper than the paid plan of Codex, Claude & Cie. More below

Paul Couvert

88,333 次观看 • 5 个月前

TETRACHROMA's first Steam demo is out now! Developing this color-changing stacker has been a joy, and I'm excited for you all to try it. The demo includes Marathon mode and a 15 puzzle preview of Puzzle mode. Let me know what you think!
0:38

TETRACHROMA's first Steam demo is out now! Developing this color-changing stacker has been a joy, and I'm excited for you all to try it. The demo includes Marathon mode and a 15 puzzle preview of Puzzle mode. Let me know what you think!

sparsevector

58,835 次观看 • 2 年前

🚨 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!
44:33

🚨 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 次观看 • 1 年前

Building an app isn’t one-size-fits-all. Watch two habit trackers built side-by-side in Antigravity using two different approaches: Fast Mode is for when the task is straightforward and you just need execution. It’s punchy, functional, and delivers at high velocity. Planning Mode is for taking a more thoughtful, scalable approach. It is designed for those who want to craft custom systems with deep, intricate logic or for follow-up tasks that require thorough context retrieval or reasoning. It may take longer, but in this mode, the Agent starts with thorough reasoning and planning, exposes implementation plan Artifacts, and focuses on self-verification.
0:48

Building an app isn’t one-size-fits-all. Watch two habit trackers built side-by-side in Antigravity using two different approaches: Fast Mode is for when the task is straightforward and you just need execution. It’s punchy, functional, and delivers at high velocity. Planning Mode is for taking a more thoughtful, scalable approach. It is designed for those who want to craft custom systems with deep, intricate logic or for follow-up tasks that require thorough context retrieval or reasoning. It may take longer, but in this mode, the Agent starts with thorough reasoning and planning, exposes implementation plan Artifacts, and focuses on self-verification.

Google Antigravity

89,391 次观看 • 6 个月前

Nothing beats open-source! We now have a fully open-source coding agent that can compete with any proprietary solution out there: • 500+ available models • It doesn't train on your code • It doesn't charge a penny for tokens • It's open. You can change if you want. Kilo Code is the #1 app on OpenRouter right now, and the community is releasing new features on GitHub at rocket speed (about 20 releases in the last 30 days). I installed it in Visual Studio Code, but you can install it in pretty much any IDE. I need to spend more time with it, but here is a very interesting design choice: Most coding agents support two modes: an "agentic" mode for writing code and an "ask" mode for talking to the model without making any changes. Kilo Code supports 5 different modes: 1. Architect mode - Research, design, and planning 2. Debug mode - Problem solving and troubleshooting 3. Code mode - To write code. 4. Ask mode - To talk to the model. 5. Orchestrator mode - Combine every agent to solve problems. On paper, I really like this. I'll need more time to try out the specialized agents and see whether niching becomes an advantage. Here is the link to the website: Thanks to the Kilo for partnering with me on this post.
6:17

Nothing beats open-source! We now have a fully open-source coding agent that can compete with any proprietary solution out there: • 500+ available models • It doesn't train on your code • It doesn't charge a penny for tokens • It's open. You can change if you want. Kilo Code is the #1 app on OpenRouter right now, and the community is releasing new features on GitHub at rocket speed (about 20 releases in the last 30 days). I installed it in Visual Studio Code, but you can install it in pretty much any IDE. I need to spend more time with it, but here is a very interesting design choice: Most coding agents support two modes: an "agentic" mode for writing code and an "ask" mode for talking to the model without making any changes. Kilo Code supports 5 different modes: 1. Architect mode - Research, design, and planning 2. Debug mode - Problem solving and troubleshooting 3. Code mode - To write code. 4. Ask mode - To talk to the model. 5. Orchestrator mode - Combine every agent to solve problems. On paper, I really like this. I'll need more time to try out the specialized agents and see whether niching becomes an advantage. Here is the link to the website: Thanks to the Kilo for partnering with me on this post.

Santiago

73,062 次观看 • 8 个月前

After creating Remodex: Codex remote control for iOS I decided to chill a bit by building a browser sidebar inside Theo - t3.gg 's T3 Code You can open it with Cmd+Shift+B This software is so easy to "manipulate" and build upon Congrats to all the guys that put the work in it because it is great I certainly will be building more things with it For this one I decided to switch from the Codex App to the Codex CLI too just to see how it works And boy it was so good
0:20

After creating Remodex: Codex remote control for iOS I decided to chill a bit by building a browser sidebar inside Theo - t3.gg 's T3 Code You can open it with Cmd+Shift+B This software is so easy to "manipulate" and build upon Congrats to all the guys that put the work in it because it is great I certainly will be building more things with it For this one I decided to switch from the Codex App to the Codex CLI too just to see how it works And boy it was so good

Emanuele Di Pietro

38,905 次观看 • 4 个月前

Spoke with Catherine Herridge about President Donald J. Trump’ plan for Gaza and how it is the only plan out there. Some of our partners in the region don't like that plan. I've met with them and spoke to them about it during my recent trip, and my response is: if you don’t like the President’s plan, then come up with a better plan.
0:51

Spoke with Catherine Herridge about President Donald J. Trump’ plan for Gaza and how it is the only plan out there. Some of our partners in the region don't like that plan. I've met with them and spoke to them about it during my recent trip, and my response is: if you don’t like the President’s plan, then come up with a better plan.

Secretary Marco Rubio

166,062 次观看 • 1 年前

This is my first full-drive on FSD V14.1.2 with Mad Max mode enabled. All I can say is, WOAH. Mad Max mode lives up to its name, it’s EPIC. It hauls ass everywhere it goes. It accelerates from a standstill very quickly, and weaves through traffic like it’s late for work. It was a totally new experience, it’s fun to use. In no way did I feel unsafe, it was actually incredibly smooth. It makes Hurry Mode feel very pedestrian. Mad Max mode will shine in more dense traffic scenarios, it will definitely save you tons of time. It’s my favorite FSD mode ever.
3:03

This is my first full-drive on FSD V14.1.2 with Mad Max mode enabled. All I can say is, WOAH. Mad Max mode lives up to its name, it’s EPIC. It hauls ass everywhere it goes. It accelerates from a standstill very quickly, and weaves through traffic like it’s late for work. It was a totally new experience, it’s fun to use. In no way did I feel unsafe, it was actually incredibly smooth. It makes Hurry Mode feel very pedestrian. Mad Max mode will shine in more dense traffic scenarios, it will definitely save you tons of time. It’s my favorite FSD mode ever.

Nic Cruz Patane

34,418 次观看 • 9 个月前

Introducing /visual-plan - a skill to generate rich, visual plans for Claude Code and Codex. Plan mode in Claude Code is incredible. But I always find my eyes glazing over when it gives me this huge markdown essay in my terminal. I found I can make much better visual plans with reusable components. So I made a skill called `/visual-plan`. It generates plans as MDX with visual, interactive components. Diagrams, interactive API specs, schema design changes, annotated code, and even pan and zoomable wireframes. So for any UI work, you can look at a wireframe first, comment on it, iterate, and then have the agent work. I’ve found this to be a much more intuitive interface for reasoning about what the agent is doing. It’s somewhat inspired by that popular post about how HTML is better than Markdown. But HTML can be slow and verbose to write. And it doesn’t look good checked into a repo. This has really made me feel like humans and engineering are entering a new abstraction phase, where we reason about things at the plan level. As long as the plan is good, agents are getting more and more reliable at executing on it. Almost to the degree that we trust the C compiler to compile to assembly reliably. Plans are the new intermediate representation. I also made a skill for the reverse of this, called `/visual-recap`. After the agent works, it gives you a recap of everything it did. Same idea: wireframes, interactive API specs and diffs, schemas, annotated code, etc. So now when you’re reviewing what the agent did for you, or looking at a pull request of somebody else’s code, you can see a visual recap instead of just reading a wall of text. It’s all free and open source. You can find it on my GitHub. Will link to it in the reply because we all know how dumb these algorithms are with links.
1:19

Introducing /visual-plan - a skill to generate rich, visual plans for Claude Code and Codex. Plan mode in Claude Code is incredible. But I always find my eyes glazing over when it gives me this huge markdown essay in my terminal. I found I can make much better visual plans with reusable components. So I made a skill called `/visual-plan`. It generates plans as MDX with visual, interactive components. Diagrams, interactive API specs, schema design changes, annotated code, and even pan and zoomable wireframes. So for any UI work, you can look at a wireframe first, comment on it, iterate, and then have the agent work. I’ve found this to be a much more intuitive interface for reasoning about what the agent is doing. It’s somewhat inspired by that popular post about how HTML is better than Markdown. But HTML can be slow and verbose to write. And it doesn’t look good checked into a repo. This has really made me feel like humans and engineering are entering a new abstraction phase, where we reason about things at the plan level. As long as the plan is good, agents are getting more and more reliable at executing on it. Almost to the degree that we trust the C compiler to compile to assembly reliably. Plans are the new intermediate representation. I also made a skill for the reverse of this, called `/visual-recap`. After the agent works, it gives you a recap of everything it did. Same idea: wireframes, interactive API specs and diffs, schemas, annotated code, etc. So now when you’re reviewing what the agent did for you, or looking at a pull request of somebody else’s code, you can see a visual recap instead of just reading a wall of text. It’s all free and open source. You can find it on my GitHub. Will link to it in the reply because we all know how dumb these algorithms are with links.

Steve (Builder.io)

124,701 次观看 • 1 个月前

Gemini 3 Flash is starting to roll out as the default model for AI Mode in Search globally. AI Mode can now tackle your most complicated questions with greater precision — without compromising speed. ⚡ With this upgrade, AI Mode becomes an all-around more powerful tool, better at understanding your needs. You can ask more nuanced questions and it will consider each aspect to provide a thoughtful response. And as always, you’ll have access to real-time information and useful links from across the web.
0:33

Gemini 3 Flash is starting to roll out as the default model for AI Mode in Search globally. AI Mode can now tackle your most complicated questions with greater precision — without compromising speed. ⚡ With this upgrade, AI Mode becomes an all-around more powerful tool, better at understanding your needs. You can ask more nuanced questions and it will consider each aspect to provide a thoughtful response. And as always, you’ll have access to real-time information and useful links from across the web.

Google

67,545 次观看 • 7 个月前

I just built an entire app in 7 minutes using Codex Spark. EveryMCP: a universal MCP server installer that configures 15+ coding agents from a single CLI command. 12 Codex Spark subagents. All running in parallel. At the same time. The project itself isn't complicated, but just imagine what this looks like when you scale the complexity. My setup: • Codex 5.3 High to plan • Codex 5.3 Medium to orchestrate • 12 Codex Spark agents (xhigh) to implement in one shot Spark isn't competing with the big models. It's a different tool entirely. You orchestrate it. You run it in swarms. And it moves at a speed that wasn't possible before, even for the top 1% of AI coders. More complex workflows coming soon. Comment below if you want me to tell you how I did it.
4:29

I just built an entire app in 7 minutes using Codex Spark. EveryMCP: a universal MCP server installer that configures 15+ coding agents from a single CLI command. 12 Codex Spark subagents. All running in parallel. At the same time. The project itself isn't complicated, but just imagine what this looks like when you scale the complexity. My setup: • Codex 5.3 High to plan • Codex 5.3 Medium to orchestrate • 12 Codex Spark agents (xhigh) to implement in one shot Spark isn't competing with the big models. It's a different tool entirely. You orchestrate it. You run it in swarms. And it moves at a speed that wasn't possible before, even for the top 1% of AI coders. More complex workflows coming soon. Comment below if you want me to tell you how I did it.

am.will

16,916 次观看 • 5 个月前

HERMES DESKTOP APP JUST GOT A NEW ULTRA MODE FOR DEEPSEEK V4 PRO – AND IT COSTS ABOUT $1 A DAY TO RUN If you're using Hermes desktop app, you're probably already running DeepSeek – it's one of the top models available. The update: → DeepSeek V4 Pro now has thinking mode, fast mode, and a brand new ultra mode → There's also an extra high mode, but the real upgrade is ultra The actual cost: roughly $1/day for a normal workflow. That's about $20-25/month – basically the same as before, just with a significantly faster mode unlocked. The verdict after a full day of testing: it flies through tool calling. Noticeably faster, same price range. If you're already paying for DeepSeek through Hermes, this is a free upgrade sitting in your settings right now. Update Hermes, grab the DeepSeek API if you don't have it yet, and try V4 Pro on ultra. Bookmark this, you'll want to come back to it later.
1:00

HERMES DESKTOP APP JUST GOT A NEW ULTRA MODE FOR DEEPSEEK V4 PRO – AND IT COSTS ABOUT $1 A DAY TO RUN If you're using Hermes desktop app, you're probably already running DeepSeek – it's one of the top models available. The update: → DeepSeek V4 Pro now has thinking mode, fast mode, and a brand new ultra mode → There's also an extra high mode, but the real upgrade is ultra The actual cost: roughly $1/day for a normal workflow. That's about $20-25/month – basically the same as before, just with a significantly faster mode unlocked. The verdict after a full day of testing: it flies through tool calling. Noticeably faster, same price range. If you're already paying for DeepSeek through Hermes, this is a free upgrade sitting in your settings right now. Update Hermes, grab the DeepSeek API if you don't have it yet, and try V4 Pro on ultra. Bookmark this, you'll want to come back to it later.

SCOTTY BEAM

24,032 次观看 • 15 天前

While we usually share a detail-packed Developer Update during a game update week, today's video is a shorter one about the launch of Custom Seas. We plan to record a full Dev Update soon looking at how the mode has landed and talking more about our approach to building on it!
1:51

While we usually share a detail-packed Developer Update during a game update week, today's video is a shorter one about the launch of Custom Seas. We plan to record a full Dev Update soon looking at how the mode has landed and talking more about our approach to building on it!

Sea of Thieves

43,179 次观看 • 1 个月前

Rare CBC panel consensus - no Carney budget makes no sense! Fred DeLorey "It goes against the entire narrative of Carney that he is the man with a plan." "That's what he told Canadians and it's why he won this last election." "They believed he had a plan and in fact he used it as an attack point. You know, a plan beats no plan." "He has no plan" Greg MacEachern "Probably going to tick off a lot of Liberals here, but I don't disagree." "I did not necessarily expect a budget. I did expect an economic update of some sort." "...There were lots of ways to communicate around this, but there's really been nothing." Fred DeLorey Greg MacEachern
3:34

Rare CBC panel consensus - no Carney budget makes no sense! Fred DeLorey "It goes against the entire narrative of Carney that he is the man with a plan." "That's what he told Canadians and it's why he won this last election." "They believed he had a plan and in fact he used it as an attack point. You know, a plan beats no plan." "He has no plan" Greg MacEachern "Probably going to tick off a lot of Liberals here, but I don't disagree." "I did not necessarily expect a budget. I did expect an economic update of some sort." "...There were lots of ways to communicate around this, but there's really been nothing." Fred DeLorey Greg MacEachern

cbcwatcher

116,957 次观看 • 1 年前

This line delivered by Commander Tiann Jerjerrod is actually the most important set up in Return of the Jedi. It tells the audience the Empire has A PLAN. RotJ director Richard Marquand has English actor Michael Pennington STOP to deliver the line which he does in a conspiratorial tone. "I tell you this station will be operational... AS PLANNED" It foreshadows that there is a Plan. The Plan is obviously to capture Luke Skywalker and destroy the Rebel fleet. The Emperor knows it. Vader knows it. Commander Jerjerrod knows it. No one else does. Certainly not any of the other grunts in the loading bay and Commander Jerjerrod's voice drops down hinting that now isn't the time to discuss it. This is what is known as good writing and directing. As always the audience is distracted by the incomplete appearance of Death Star 2 and the Dad Joke one-liner Vader delivers next with "The Emperor is not as forgiving as I am."
2:53

This line delivered by Commander Tiann Jerjerrod is actually the most important set up in Return of the Jedi. It tells the audience the Empire has A PLAN. RotJ director Richard Marquand has English actor Michael Pennington STOP to deliver the line which he does in a conspiratorial tone. "I tell you this station will be operational... AS PLANNED" It foreshadows that there is a Plan. The Plan is obviously to capture Luke Skywalker and destroy the Rebel fleet. The Emperor knows it. Vader knows it. Commander Jerjerrod knows it. No one else does. Certainly not any of the other grunts in the loading bay and Commander Jerjerrod's voice drops down hinting that now isn't the time to discuss it. This is what is known as good writing and directing. As always the audience is distracted by the incomplete appearance of Death Star 2 and the Dad Joke one-liner Vader delivers next with "The Emperor is not as forgiving as I am."

Donald Ward

205,921 次观看 • 2 个月前