Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

This is how i build everything now. Before the agents touch a line of code "before you do any building make 10 mock ups in html of how we can make it look" I then pick a path and ask for more mockups until I feel happy with the... show more

0xSero

21,879 subscribers

25,695 views • 4 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

My favorite way of interacting with Claude Code is to have it generate static HTML files as outputs (reports, explorations, code structure, mockups etc.) I wanted to iterate on the file by commenting in browser and having Claude update the output live. So, I built this Claude Skill👇 How it works: - Install Claude Code skill (ask it to clone repo) - Build an HTML page for anything (e.g. research coding agents and generate HTML report) - Ask it to make the page interactive That's it. CC will launch a localhost server and allow you to then leave comments on the page itself and once it updates, will give you a tour of changes. It's like Google Docs kind of comments/iteration but for HTML pages.

My favorite way of interacting with Claude Code is to have it generate static HTML files as outputs (reports, explorations, code structure, mockups etc.) I wanted to iterate on the file by commenting in browser and having Claude update the output live. So, I built this Claude Skill👇 How it works: - Install Claude Code skill (ask it to clone repo) - Build an HTML page for anything (e.g. research coding agents and generate HTML report) - Ask it to make the page interactive That's it. CC will launch a localhost server and allow you to then leave comments on the page itself and once it updates, will give you a tour of changes. It's like Google Docs kind of comments/iteration but for HTML pages.

Paras Chopra

215,218 views • 2 months ago

I make a custom sandbox 100% of the time I build anything now this has been the biggest change in how I work, almost as impactful as having agents write code for me. Bespoke editors too cheap to meter, making the craft and polish step way more enjoyable

I make a custom sandbox 100% of the time I build anything now this has been the biggest change in how I work, almost as impactful as having agents write code for me. Bespoke editors too cheap to meter, making the craft and polish step way more enjoyable

Amelia Wattenberger 🪷

38,443 views • 3 months ago

"I cannot surround people with things that are underperforming the quality of engineering we want to do." "The most fundamental design error that you can possibly make is create a falseness in a product that make people predictably do the wrong thing. So I make a big deal out of these kind of things. I cannot surround people with things that are underperforming the quality of engineering we want to do. And that's down to the detail of the doors in the office. From the inside perspective, you have to sweat all the details. The way you do anything is how you do everything." —tobi lutke

"I cannot surround people with things that are underperforming the quality of engineering we want to do." "The most fundamental design error that you can possibly make is create a falseness in a product that make people predictably do the wrong thing. So I make a big deal out of these kind of things. I cannot surround people with things that are underperforming the quality of engineering we want to do. And that's down to the detail of the doors in the office. From the inside perspective, you have to sweat all the details. The way you do anything is how you do everything." —tobi lutke

David Senra

78,527 views • 6 months ago

Dana White wants to be the CEO of boxing: 🗣️ “This is how you build an NFL or NBA. This is how it’s done. I feel like we’re starting from scratch now with boxing. I believe we can do it again… You’ll actually know some of these champions now.”

Dana White wants to be the CEO of boxing: 🗣️ “This is how you build an NFL or NBA. This is how it’s done. I feel like we’re starting from scratch now with boxing. I believe we can do it again… You’ll actually know some of these champions now.”

Happy Punch

308,790 views • 10 months ago

This isn't the Universal Century timeline, so you can feel at ease, but I don't know how they do it in the Build series. Sometimes, things get way too serious, even though it's just plastic models fighting each other. They make it seem like things are actually at stake, even though everything and everyone is safe. How do they bring such seriousness??? I don't know, but I feel it sometimes. Like here, I feel so bad.

This isn't the Universal Century timeline, so you can feel at ease, but I don't know how they do it in the Build series. Sometimes, things get way too serious, even though it's just plastic models fighting each other. They make it seem like things are actually at stake, even though everything and everyone is safe. How do they bring such seriousness??? I don't know, but I feel it sometimes. Like here, I feel so bad.

HIM'EL 🗡️ 勇者 #ThankYouMiura

97,816 views • 10 months ago

Hassett: "The way to think about what AI and its agents can do is they can act as if they're the best coach you've ever had for whatever job you have. And so while you're trying to figure out, how do I make my boss happy? How do I do what it takes to make the firm successful? It's like you've got a coach right there with you every step of the way."

Hassett: "The way to think about what AI and its agents can do is they can act as if they're the best coach you've ever had for whatever job you have. And so while you're trying to figure out, how do I make my boss happy? How do I do what it takes to make the firm successful? It's like you've got a coach right there with you every step of the way."

Aaron Rupar

25,417 views • 7 months ago

Logan Paul explains how focusing on the right things made money follow ''Money seems to be a byproduct of the things I love doing. I made YT videos for 10 years before anyone realized that you could become a YouTuber and make a career out of it'' ''I played thousands of hours of the Pokémon games before I ever made a penny from Pokémon, and Pokémon in particular is the perfect fit for me. It's business, it's passion, and it's content, and Pokémon checks all these boxes'' ''I get to do a lot of things where I can sit in that pocket''

Logan Paul explains how focusing on the right things made money follow ''Money seems to be a byproduct of the things I love doing. I made YT videos for 10 years before anyone realized that you could become a YouTuber and make a career out of it'' ''I played thousands of hours of the Pokémon games before I ever made a penny from Pokémon, and Pokémon in particular is the perfect fit for me. It's business, it's passion, and it's content, and Pokémon checks all these boxes'' ''I get to do a lot of things where I can sit in that pocket''

Mikli

159,026 views • 5 months ago

There's so much focus on "how can AI do my work for me?" I think the more important question is "what work can I now do with AI that I would have never attempted before?" Earlier this year I wrote freestiler, a vector tiling engine for R and Python, with the help of Claude and Codex. I knew what the ideal engine looked like and how it would work at a high level. I didn't know how to put it together, and I don't know Rust, the language I wanted under the hood. Previously I would never have attempted this project as the ROI wasn't there. It would have taken me a year or more to learn the internals of a vector tiling engine and enough Rust to implement one. With Opus-level models, I could take it on. freestiler now powers all my vector tiling pipelines, including the map below rendering 143 million jobs from LODES, and it has 114 GitHub stars. Building this way has required a different set of skills. I don't review the code line by line. I set up adversarial agents to do that and write the test suites. What I review is the architecture, the behavior, and the results. Agent teams surface findings and explain their reasoning; I evaluate and critique. My job isn't to stress over code formatting, but instead to focus on questions like whether the engine is designed right, whether the output is correct, and if the UX makes sense. This means that I haven't "replaced my work." I've taken on entirely new work, with the help of agents, that I would have never done otherwise. It has taken some getting used to shipping code I haven't personally typed. In the old way of working, I built understanding through writing that code. Now I build understanding through managing the project - writing a spec, reviewing structure, evaluating UX. And that's helped me think a whole lot bigger in terms of what I can now do.

There's so much focus on "how can AI do my work for me?" I think the more important question is "what work can I now do with AI that I would have never attempted before?" Earlier this year I wrote freestiler, a vector tiling engine for R and Python, with the help of Claude and Codex. I knew what the ideal engine looked like and how it would work at a high level. I didn't know how to put it together, and I don't know Rust, the language I wanted under the hood. Previously I would never have attempted this project as the ROI wasn't there. It would have taken me a year or more to learn the internals of a vector tiling engine and enough Rust to implement one. With Opus-level models, I could take it on. freestiler now powers all my vector tiling pipelines, including the map below rendering 143 million jobs from LODES, and it has 114 GitHub stars. Building this way has required a different set of skills. I don't review the code line by line. I set up adversarial agents to do that and write the test suites. What I review is the architecture, the behavior, and the results. Agent teams surface findings and explain their reasoning; I evaluate and critique. My job isn't to stress over code formatting, but instead to focus on questions like whether the engine is designed right, whether the output is correct, and if the UX makes sense. This means that I haven't "replaced my work." I've taken on entirely new work, with the help of agents, that I would have never done otherwise. It has taken some getting used to shipping code I haven't personally typed. In the old way of working, I built understanding through writing that code. Now I build understanding through managing the project - writing a spec, reviewing structure, evaluating UX. And that's helped me think a whole lot bigger in terms of what I can now do.

Kyle Walker

13,740 views • 22 days ago

A little sneak peak at what I am building with Brayden Levangie using the X API. A new kind of personalized X is now possible. And it comes with many side benefits I haven’t yet shown here. Like feeds for your OpenClaw🦞 And reports that go way being what you can make with AIs that aren’t cognitive architectures. This is how I keep up now on the AI industry here on X. Looking for help to turn this into a business. Sponsors and customers who need much better reports on what is happening right now. What do you wish this effort would show you? By the way. I did ask this without writing a line of code. Brayden’s agents did it all.

A little sneak peak at what I am building with Brayden Levangie using the X API. A new kind of personalized X is now possible. And it comes with many side benefits I haven’t yet shown here. Like feeds for your OpenClaw🦞 And reports that go way being what you can make with AIs that aren’t cognitive architectures. This is how I keep up now on the AI industry here on X. Looking for help to turn this into a business. Sponsors and customers who need much better reports on what is happening right now. What do you wish this effort would show you? By the way. I did ask this without writing a line of code. Brayden’s agents did it all.

Robert Scoble

67,641 views • 5 months ago

You can enroll in my animation course for the next 10 days! It's the perfect way to learn the theory behind great animations, but also how to build them in code. Now with a skill file for agents. We'll cover all of these components and more, source code included.

You can enroll in my animation course for the next 10 days! It's the perfect way to learn the theory behind great animations, but also how to build them in code. Now with a skill file for agents. We'll cover all of these components and more, source code included.

Emil Kowalski

559,147 views • 6 months ago

You can now make videos like this using HTML. I didn’t believe it at first until the HyperFrames team showed me how they do it directly in Codex and Claude Code. Best of all, the tool is 100% free and open source. But you need to learn the right workflows to make the videos look great - including generating a frame.md, storyboards, and more. 📌 Subscribe to get our full tutorial tomorrow:

You can now make videos like this using HTML. I didn’t believe it at first until the HyperFrames team showed me how they do it directly in Codex and Claude Code. Best of all, the tool is 100% free and open source. But you need to learn the right workflows to make the videos look great - including generating a frame.md, storyboards, and more. 📌 Subscribe to get our full tutorial tomorrow:

Peter Yang

192,049 views • 1 month ago

For those of you tired of yet another AI-based IDE: Check out Traycer. It's a Visual Studio Code extension (free forever for anyone working on open-source repositories), and it does something different from everyone else. You write a high-level prompt outlining the changes you want to make to your codebase, and the extension generates a plan for you before you touch the code. (It reminds me of GitHub Copilot Workspaces.) You can review the plan, understand exactly the changes the extension will make to your code, and make any modifications. When you are ready, you execute the plan, and Traycer stages all of the changes so you have a new opportunity to review everything. Only then does Traycer apply the changes. This is ideal for large codebases where you'd rather study the changes the AI plans to make before they make it into your code. Look at the video I recorded to see how it works. Thanks to the Traycer team for collaborating with me on this post!

For those of you tired of yet another AI-based IDE: Check out Traycer. It's a Visual Studio Code extension (free forever for anyone working on open-source repositories), and it does something different from everyone else. You write a high-level prompt outlining the changes you want to make to your codebase, and the extension generates a plan for you before you touch the code. (It reminds me of GitHub Copilot Workspaces.) You can review the plan, understand exactly the changes the extension will make to your code, and make any modifications. When you are ready, you execute the plan, and Traycer stages all of the changes so you have a new opportunity to review everything. Only then does Traycer apply the changes. This is ideal for large codebases where you'd rather study the changes the AI plans to make before they make it into your code. Look at the video I recorded to see how it works. Thanks to the Traycer team for collaborating with me on this post!

Santiago

84,445 views • 1 year ago

#FirstKhaotung #เฟิร์สข้าวตัง they’ve actually been close since before the eclipse, WAY BEFORE that, crying 🗣️: first and khaotung, you guys are actually close friends in real life, right? how does it feel to be acting together? 🐈‍⬛: normally, whenever i receive a script for any series, i'm always happy and excited but this time, i feel it’s more special than ever, it's like an extension of our real/life friendship into the series' characters. i feel that an opportunity like this working with a partner you fully trust and can be yourself around, doesn’t happen often, that’s why i want to make the most of this opportunity 🗣️: how many years have you been waiting to work together? 🐈: since we first met, it’s been about 4 or 5 years, this is the first time we work together as lead, let's see how chaotic it gets...just kidding😭let's see how it turns out. 🗣️: since you're so close, did you feel shy or … filming the love scenes? 🐈: i did feel a bit shy while filming the pilot 🗣️: when did you shy? you didn't

#FirstKhaotung #เฟิร์สข้าวตัง they’ve actually been close since before the eclipse, WAY BEFORE that, crying 🗣️: first and khaotung, you guys are actually close friends in real life, right? how does it feel to be acting together? 🐈‍⬛: normally, whenever i receive a script for any series, i'm always happy and excited but this time, i feel it’s more special than ever, it's like an extension of our real/life friendship into the series' characters. i feel that an opportunity like this working with a partner you fully trust and can be yourself around, doesn’t happen often, that’s why i want to make the most of this opportunity 🗣️: how many years have you been waiting to work together? 🐈: since we first met, it’s been about 4 or 5 years, this is the first time we work together as lead, let's see how chaotic it gets...just kidding😭let's see how it turns out. 🗣️: since you're so close, did you feel shy or … filming the love scenes? 🐈: i did feel a bit shy while filming the pilot 🗣️: when did you shy? you didn't

Thalía

15,175 views • 3 months ago

sometimes I need to swiftie in a specific way and right now that way is making this audio and putting it with this clip from the end of the new eras tour movie. this is how I feel.

sometimes I need to swiftie in a specific way and right now that way is making this audio and putting it with this clip from the end of the new eras tour movie. this is how I feel.

taylor

44,308 views • 7 months ago

Them: “I wish I had your motivation, time and genetics” Me: “Being fat is a choice…. It has nothing to do with motivation, time or genetics. It has everything to do with discipline, and doing the work regardless of how you feel.”

Them: “I wish I had your motivation, time and genetics” Me: “Being fat is a choice…. It has nothing to do with motivation, time or genetics. It has everything to do with discipline, and doing the work regardless of how you feel.”

Gia Macool

16,474 views • 3 months ago

🖤: "Lastly, could you please do a 3-line acrostic poem for me?" 🩷: "No, no. 3-line acrostic poem is a bit of a burden for me. I actually have something I want to say to Hamin." 🖤: "Oh you do? What is it?" 🩷: "Of course I do." 🩷: "Honestly, I'm someone who express myself more to Hamin, right?" 💙🖤: "Yeah." 🩷: "(There's a reason) how that could happen. Hamin is actually a maknae but even so he takes care of the hyungs very well. To me, also, I could feel how I'm being taken care of (by him) a lot. As a fellow Dance line, when we work and make choreography (together), we rely on each other a lot. I also rely on him a lot. Usually, Hamin also like 'how is it? how is that?' (discuss things) to me and it makes me feel good. So now, I feel like without Haminnie I can't do anything. So on his birthday today, I want to express my gratitude to him." 🩷: "Now, I can't do anything if you are not there." 💙🖤: "Woah..." 🩷: "That's the truth. As PLAVE member too, when we work together, when you are there... I don't know. I'm just glad you are here." 🖤: "Me too." 🩷: "It's the truth, really." 🖤: "Same goes for me." 🩷: "From the bottom of my heart." 🖤: "For Bamby hyung to be able saying things like this seems hard (for him) so I could also feel how much he likes me." 🩷: "Exactly, I hope you can feel more (of his affection) but it seems like I can't show much of it." 🖤: "No, no. As for me, of course I feel the same way for other members too, but there's something that makes me feel good towards you. So I want to make you feel good too." 🩷: "That's right, we always have a lot of fun." 🖤: "Even though we see each other all the time, hearing this words from you..." 🩷: "It feels different." 🖤: "It does and I like it." 💙: "WHAT THE?? ISN'T IT HEART SIGNAL?????" 🩷: 😂😂😂 🖤: "Ahh... You are not leaving yet???"

🖤: "Lastly, could you please do a 3-line acrostic poem for me?" 🩷: "No, no. 3-line acrostic poem is a bit of a burden for me. I actually have something I want to say to Hamin." 🖤: "Oh you do? What is it?" 🩷: "Of course I do." 🩷: "Honestly, I'm someone who express myself more to Hamin, right?" 💙🖤: "Yeah." 🩷: "(There's a reason) how that could happen. Hamin is actually a maknae but even so he takes care of the hyungs very well. To me, also, I could feel how I'm being taken care of (by him) a lot. As a fellow Dance line, when we work and make choreography (together), we rely on each other a lot. I also rely on him a lot. Usually, Hamin also like 'how is it? how is that?' (discuss things) to me and it makes me feel good. So now, I feel like without Haminnie I can't do anything. So on his birthday today, I want to express my gratitude to him." 🩷: "Now, I can't do anything if you are not there." 💙🖤: "Woah..." 🩷: "That's the truth. As PLAVE member too, when we work together, when you are there... I don't know. I'm just glad you are here." 🖤: "Me too." 🩷: "It's the truth, really." 🖤: "Same goes for me." 🩷: "From the bottom of my heart." 🖤: "For Bamby hyung to be able saying things like this seems hard (for him) so I could also feel how much he likes me." 🩷: "Exactly, I hope you can feel more (of his affection) but it seems like I can't show much of it." 🖤: "No, no. As for me, of course I feel the same way for other members too, but there's something that makes me feel good towards you. So I want to make you feel good too." 🩷: "That's right, we always have a lot of fun." 🖤: "Even though we see each other all the time, hearing this words from you..." 🩷: "It feels different." 🖤: "It does and I like it." 💙: "WHAT THE?? ISN'T IT HEART SIGNAL?????" 🩷: 😂😂😂 🖤: "Ahh... You are not leaving yet???"

it is rain

27,509 views • 1 year ago

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.

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)

124,409 views • 1 month ago

How to Disappear is now yours. It has brought all of us closer than ever before, and we genuinely couldn’t be more proud of the body of work we have created. Now you can experience it for yourself, to interpret and relate to it in a way that only you can.

How to Disappear is now yours. It has brought all of us closer than ever before, and we genuinely couldn’t be more proud of the body of work we have created. Now you can experience it for yourself, to interpret and relate to it in a way that only you can.

Casey

50,974 views • 2 years ago