Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Warp now has vertical tabs. - View coding agents with status indicators to see what's done, blocked, or still cooking - Double-click to rename or colorize tabs - Customize what you see: directory, branch name, conversation, etc Just enable in Settings > Appearance > Tabs

warpdotdev's profile picture

Warp

57,112 subscribers

448,177 görüntüleme • 3 ay önce •via X (Twitter)

KomediEğitimBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Google Chrome now has vertical tabs, but they might not be enabled by default for you. Here’s what you need to do: - Go to the Chrome flags section, search for "vertical tabs", enable it, and relaunch the browser. - After that, right-click on the empty space next to a tab and click on "Move tabs to side".
0:38

Google Chrome now has vertical tabs, but they might not be enabled by default for you. Here’s what you need to do: - Go to the Chrome flags section, search for "vertical tabs", enable it, and relaunch the browser. - After that, right-click on the empty space next to a tab and click on "Move tabs to side".

AshutoshShrivastava

26,794 görüntüleme • 3 ay önce

introducing @tabseditor The AI doc editor that writes with you. Tabs is a simple editor to write documents with AI to assist you. > import docs from google drive, MS one drive or create new doc > bring in your files and web links as context > chat with tabs all web. enjoy.
0:49

introducing @tabseditor The AI doc editor that writes with you. Tabs is a simple editor to write documents with AI to assist you. > import docs from google drive, MS one drive or create new doc > bring in your files and web links as context > chat with tabs all web. enjoy.

Afolabi Sokeye 🧱

203,820 görüntüleme • 10 ay önce

PSA: You can vibe code your own "New tab" page in Chrome. I have turned mine into the ultimate solution to the "too many tabs" problem - See all your tabs with clear titles, grouped by domain - Closing any tab gives you "swoosh" sound and confetti effect 🎊 - "Easy wins" grouped together: homepages, localhost tabs... batch-close them with one click - Duplicate tabs detected; close duplicates with one click - For tabs you're not done with, save it for later in a checklist This is the Marie Kondo method for browser tabs Open-sourced the code below
0:32

PSA: You can vibe code your own "New tab" page in Chrome. I have turned mine into the ultimate solution to the "too many tabs" problem - See all your tabs with clear titles, grouped by domain - Closing any tab gives you "swoosh" sound and confetti effect 🎊 - "Easy wins" grouped together: homepages, localhost tabs... batch-close them with one click - Duplicate tabs detected; close duplicates with one click - For tabs you're not done with, save it for later in a checklist This is the Marie Kondo method for browser tabs Open-sourced the code below

Zara Zhang

424,968 görüntüleme • 3 ay önce

No way this isn’t the future of browsing. Safari in visionOS 27 lets you view up to five tabs side by side in a carousel of webpages, each as large as a poster, making it much easier to compare products, services, or travel accommodations. It’s also a major productivity boost for anyone who needs to monitor multiple sources of information at once or frequently jump between different websites. Instead of managing tabs, you can simply see everything at a glance. Super cool.
0:25

No way this isn’t the future of browsing. Safari in visionOS 27 lets you view up to five tabs side by side in a carousel of webpages, each as large as a poster, making it much easier to compare products, services, or travel accommodations. It’s also a major productivity boost for anyone who needs to monitor multiple sources of information at once or frequently jump between different websites. Instead of managing tabs, you can simply see everything at a glance. Super cool.

Phil Traut ᯅ

32,240 görüntüleme • 1 ay önce

CSS Trick 🤙 You can create these tab bar controls by using :has() to count the number of tabs ⭐️ .tabs:has(input:nth-of-type(3)){--count: 3;} .tabs:has(:checked:nth-of-type(3)){--active: 200%;} .tabs::after{ translate:var(--active) 0;} Let's break it down in this ! 📼 Couple of CSS :has() tricks here combined with custom properties 😎 First things first, lay out the tabs using display: grid. This gives you a way to create equal-width tabs 🙏 .tabs { display: grid; grid-auto-flow: column; } Then you use :has() to count the number of tabs and store that in a custom property 🤓 .tabs:has(input:nth-of-type(3)) { --count: 3; } .tabs:has(input:nth-of-type(4)) { --count: 4; } Using the cascade, the last valid :has() gives you the number of tabs 🫶 Using the tab count, you can size the tab indicator. For the tab indicator, use the tabs pseudoelement: .tabs::after { content: ""; position: absolute; height: 100%; width: calc(100% / var(--count)); } See how you can use --count to determine its size 📏 Next, use :has() to determine which tab is active or :checked with input [type=radio] .tabs:has(:checked:nth-of-type(2)) { --active: 1; } .tabs:has(:checked:nth-of-type(3)) { --active: 2; } You can use a zero-indexed translation here. If the second input is :checked, set --active: 1, then translate the pseudoelement on the tabs to that position 👉 .tabs::after { translate: calc(var(--active, 0) * 100%) 0; } Or you could set active to the translation: .tabs:has(:checked:nth-of-type(2)) { --active: 100%; } Setting the custom property allows you to use the index elsewhere if you need it 🤙 The final piece is using mix-blend-mode 👀 The tabs have a black background-color, the pseudoelement is white, and the label text is white. When you use mix-blend-mode: difference on the pseudoelement it will give this effect that the text transitions from white to black sliding across 😎 .tabs::after { color: hsl(0 0% 100%); mix-blend-mode: difference; } You can totally mix up the colors here though and go with a different effect. The mechanics of how you can use CSS :has() is the main point here 🙏 As always, any questions, suggestions, etc. let me know CodePen.IO link below! 👇 (There's even a Tailwind CSS play for this one too 👀)
9:24

CSS Trick 🤙 You can create these tab bar controls by using :has() to count the number of tabs ⭐️ .tabs:has(input:nth-of-type(3)){--count: 3;} .tabs:has(:checked:nth-of-type(3)){--active: 200%;} .tabs::after{ translate:var(--active) 0;} Let's break it down in this ! 📼 Couple of CSS :has() tricks here combined with custom properties 😎 First things first, lay out the tabs using display: grid. This gives you a way to create equal-width tabs 🙏 .tabs { display: grid; grid-auto-flow: column; } Then you use :has() to count the number of tabs and store that in a custom property 🤓 .tabs:has(input:nth-of-type(3)) { --count: 3; } .tabs:has(input:nth-of-type(4)) { --count: 4; } Using the cascade, the last valid :has() gives you the number of tabs 🫶 Using the tab count, you can size the tab indicator. For the tab indicator, use the tabs pseudoelement: .tabs::after { content: ""; position: absolute; height: 100%; width: calc(100% / var(--count)); } See how you can use --count to determine its size 📏 Next, use :has() to determine which tab is active or :checked with input [type=radio] .tabs:has(:checked:nth-of-type(2)) { --active: 1; } .tabs:has(:checked:nth-of-type(3)) { --active: 2; } You can use a zero-indexed translation here. If the second input is :checked, set --active: 1, then translate the pseudoelement on the tabs to that position 👉 .tabs::after { translate: calc(var(--active, 0) * 100%) 0; } Or you could set active to the translation: .tabs:has(:checked:nth-of-type(2)) { --active: 100%; } Setting the custom property allows you to use the index elsewhere if you need it 🤙 The final piece is using mix-blend-mode 👀 The tabs have a black background-color, the pseudoelement is white, and the label text is white. When you use mix-blend-mode: difference on the pseudoelement it will give this effect that the text transitions from white to black sliding across 😎 .tabs::after { color: hsl(0 0% 100%); mix-blend-mode: difference; } You can totally mix up the colors here though and go with a different effect. The mechanics of how you can use CSS :has() is the main point here 🙏 As always, any questions, suggestions, etc. let me know CodePen.IO link below! 👇 (There's even a Tailwind CSS play for this one too 👀)

jhey ʕ•ᴥ•ʔ

70,730 görüntüleme • 2 yıl önce

So excited for Agent view (research preview) in Claude Code. Run claude agents to list and start multiple sessions. Each one runs w/o taking up a terminal tab. See what's running, what's blocked, and what's done. Reply inline or jump in and out of sessions with ease.
0:38

So excited for Agent view (research preview) in Claude Code. Run claude agents to list and start multiple sessions. Each one runs w/o taking up a terminal tab. See what's running, what's blocked, and what's done. Reply inline or jump in and out of sessions with ease.

Ado

22,471 görüntüleme • 2 ay önce

CSS Tip! 💪 You can create these tab controls with CSS :has() + radio buttons ✨ .tabs:has(input:nth-of-type(3)) { --count: 3; } .tabs:has(:checked:nth-of-type(3)) { --active: 2; } .tabs::after { translate: calc(var(--active, 0) * 100%) 0; width: calc(100% / var(--count)); } Two CSS :has() tricks here combined with a rendering trick 🤙 The tab control is a container using display: grid. You can use :has() to count the number of tabs in the container: .tabs:has(input:nth-of-type(3)) { --count: 3; } .tabs:has(input:nth-of-type(4)) { --count: 4; } Using the cascade, the last valid :has() gives you the number of tabs 🫶 Once you know the number of tabs, you know how to size the indicator: .tabs::after { content: ""; position: absolute; height: 100%; width: calc(100% / var(--count)); } It's a pseudoelement that uses --count to determine its size 📏 The next :has() trick is determining which tab is active or :checked as it's an input [type=radio] .tabs:has(:checked:nth-of-type(2)) { --active: 1; } .tabs:has(:checked:nth-of-type(3)) { --active: 2; } You can use a zero-indexed translation here. If the second input is :checked, set --active: 1, then translate the pseudoelement on the tabs to that position 👉 .tabs::after { translate: calc(var(--active, 0) * 100%) 0; } The last rendering trick is using mix-blend-mode 👀 The tabs have a black background-color, the pseudoelement is white, and the label text is white. When you use mix-blend-mode: difference on the pseudoelement it will give this effect that the text transitions from white to black sliding across 😎 .tabs::after { color: hsl(0 0% 100%); mix-blend-mode: difference; } You can totally mix up the colors here though and go with a different effect. The mechanics of how you can use CSS :has() is the main point here 🙏 As always, any questions, suggestions, etc. let me know CodePen.IO link below! 👇 (There's even a Tailwind CSS play for this one too 👀)
0:48

CSS Tip! 💪 You can create these tab controls with CSS :has() + radio buttons ✨ .tabs:has(input:nth-of-type(3)) { --count: 3; } .tabs:has(:checked:nth-of-type(3)) { --active: 2; } .tabs::after { translate: calc(var(--active, 0) * 100%) 0; width: calc(100% / var(--count)); } Two CSS :has() tricks here combined with a rendering trick 🤙 The tab control is a container using display: grid. You can use :has() to count the number of tabs in the container: .tabs:has(input:nth-of-type(3)) { --count: 3; } .tabs:has(input:nth-of-type(4)) { --count: 4; } Using the cascade, the last valid :has() gives you the number of tabs 🫶 Once you know the number of tabs, you know how to size the indicator: .tabs::after { content: ""; position: absolute; height: 100%; width: calc(100% / var(--count)); } It's a pseudoelement that uses --count to determine its size 📏 The next :has() trick is determining which tab is active or :checked as it's an input [type=radio] .tabs:has(:checked:nth-of-type(2)) { --active: 1; } .tabs:has(:checked:nth-of-type(3)) { --active: 2; } You can use a zero-indexed translation here. If the second input is :checked, set --active: 1, then translate the pseudoelement on the tabs to that position 👉 .tabs::after { translate: calc(var(--active, 0) * 100%) 0; } The last rendering trick is using mix-blend-mode 👀 The tabs have a black background-color, the pseudoelement is white, and the label text is white. When you use mix-blend-mode: difference on the pseudoelement it will give this effect that the text transitions from white to black sliding across 😎 .tabs::after { color: hsl(0 0% 100%); mix-blend-mode: difference; } You can totally mix up the colors here though and go with a different effect. The mechanics of how you can use CSS :has() is the main point here 🙏 As always, any questions, suggestions, etc. let me know CodePen.IO link below! 👇 (There's even a Tailwind CSS play for this one too 👀)

jhey ʕ•ᴥ•ʔ

437,533 görüntüleme • 2 yıl önce

THIS GUY BUILT A COMMAND CENTER FOR MANAGING AI AGENT TEAMS he was running 20+ agents through openclaw. all from terminal tabs and Discord. 12 tabs open. still losing track of who's doing what. which cron failed. so he built a dashboard that gives you one place to see everything: > org map showing the full agent hierarchy, who reports to who and what tools each agent has > chat with any agent through a real UI instead of bouncing between terminals > kanban board for tracking tasks across all agents > cron monitor with pipeline visualizations so you can see which jobs are failing > memory browser to read through all agent knowledge files in one place you can even point it at your openclaw workspace and it auto-discovers every agent from their config files. zero setup. AND ITS OPEN SOURCE TOO.
1:06

THIS GUY BUILT A COMMAND CENTER FOR MANAGING AI AGENT TEAMS he was running 20+ agents through openclaw. all from terminal tabs and Discord. 12 tabs open. still losing track of who's doing what. which cron failed. so he built a dashboard that gives you one place to see everything: > org map showing the full agent hierarchy, who reports to who and what tools each agent has > chat with any agent through a real UI instead of bouncing between terminals > kanban board for tracking tasks across all agents > cron monitor with pipeline visualizations so you can see which jobs are failing > memory browser to read through all agent knowledge files in one place you can even point it at your openclaw workspace and it auto-discovers every agent from their config files. zero setup. AND ITS OPEN SOURCE TOO.

Om Patel

46,780 görüntüleme • 4 ay önce

Seeing ads on YouTube or another site? Manually update our built-in ad blocker to ensure you have the latest changes. On desktop, go to Settings > Shields > Content filtering and click the "Update lists" button Then refresh the tab where you saw ads and see if it's fixed.
0:22

Seeing ads on YouTube or another site? Manually update our built-in ad blocker to ensure you have the latest changes. On desktop, go to Settings > Shields > Content filtering and click the "Update lists" button Then refresh the tab where you saw ads and see if it's fixed.

Brave

49,441 görüntüleme • 1 yıl önce

THIS GUY GOT SICK OF OPENING 30 TABS ON WIKIPEDIA SO HE VIBE CODED A VISUAL BROWSER FOR IT we all know the wikipedia rabbit hole. you click one article, then another link inside it, then another, then another. 30 tabs deep and you forgot where you started this guy built a canvas based browser where every article you click opens as a card on an infinite canvas. every link between articles is a visible connection you can: > look up any article > browse the home screen > draw connections > add post-it nodes > even save your boards locally instead of losing yourself in tabs you can see your entire research path laid out visually like a mind map click an article. the linked topics branch out around it. click one of those. it branches further. your entire rabbit hole is one visual map you can zoom in and out of someone said that this should exist for the entire internet the concept is called "canvas-like browsing" and its a great way to do research reading wikipedia has always been the best way to learn about anything and now you can actually see how everything connects
0:49

THIS GUY GOT SICK OF OPENING 30 TABS ON WIKIPEDIA SO HE VIBE CODED A VISUAL BROWSER FOR IT we all know the wikipedia rabbit hole. you click one article, then another link inside it, then another, then another. 30 tabs deep and you forgot where you started this guy built a canvas based browser where every article you click opens as a card on an infinite canvas. every link between articles is a visible connection you can: > look up any article > browse the home screen > draw connections > add post-it nodes > even save your boards locally instead of losing yourself in tabs you can see your entire research path laid out visually like a mind map click an article. the linked topics branch out around it. click one of those. it branches further. your entire rabbit hole is one visual map you can zoom in and out of someone said that this should exist for the entire internet the concept is called "canvas-like browsing" and its a great way to do research reading wikipedia has always been the best way to learn about anything and now you can actually see how everything connects

Om Patel

14,455 görüntüleme • 2 ay önce

From across town to across the world, VP of Global Scouting, Luca Desta, is keeping tabs on players and helping grow the game. Get a glimpse at what his life is like in working with NBA Africa on the latest 𝐅𝐫𝐨𝐧𝐭 𝐑𝐨𝐰𝐞 🏀 Now on JAZZ+ or wherever you get podcasts 👇
0:27

From across town to across the world, VP of Global Scouting, Luca Desta, is keeping tabs on players and helping grow the game. Get a glimpse at what his life is like in working with NBA Africa on the latest 𝐅𝐫𝐨𝐧𝐭 𝐑𝐨𝐰𝐞 🏀 Now on JAZZ+ or wherever you get podcasts 👇

Utah Jazz

22,678 görüntüleme • 2 yıl önce

🚨 𝕏 NEW FEATURE 🚨 𝕏 has just launched 'Global Trending', a new section that lets you see what is trending across the world in real time. Browse by category or pick a specific country to see what people are talking about globally. Explore > Trending
0:29

🚨 𝕏 NEW FEATURE 🚨 𝕏 has just launched 'Global Trending', a new section that lets you see what is trending across the world in real time. Browse by category or pick a specific country to see what people are talking about globally. Explore > Trending

DogeDesigner

32,799 görüntüleme • 7 ay önce

long time no posting, here's some of the stuff we released in helium recently: - customizable keyboard shortcuts on all platforms - automatic updates on windows - frameless mode (previously zen mode), with floating sidebar, is now out of beta and included in settings by default - improved fingerprint noising: fixed the canvas noising algorithm and added protections against analysis attacks (thank you Cynthia 🐈 for your report, research, and assistance) - tab URL copying, one or multiple, formatted as a list with line breaks - manual tab hibernation, with an option to hibernate all tabs except for selected/active ones - an option to close tabs to the left (or above, in vertical layout) - redesigned toast notifications, now anchored to the active web page, and no longer blinding in dark mode - toast notification about newly opened background tabs in frameless mode (can be disabled in settings) - redesigned the infobar, it no longer looks out of place - improved QR code generation, now it's actually useful - downloads bubble is now shown instead of the full page whenever applicable - kagi search now supports reverse image search from image context menu - frameless mode animations are now smoother - better color contrast in light and dark modes - a lot of bug fixes and other minor improvements all of these changes are present in the latest version of helium. if you're using helium on windows, please update to the latest version, so your browser can be updated automatically from now on!
0:45

long time no posting, here's some of the stuff we released in helium recently: - customizable keyboard shortcuts on all platforms - automatic updates on windows - frameless mode (previously zen mode), with floating sidebar, is now out of beta and included in settings by default - improved fingerprint noising: fixed the canvas noising algorithm and added protections against analysis attacks (thank you Cynthia 🐈 for your report, research, and assistance) - tab URL copying, one or multiple, formatted as a list with line breaks - manual tab hibernation, with an option to hibernate all tabs except for selected/active ones - an option to close tabs to the left (or above, in vertical layout) - redesigned toast notifications, now anchored to the active web page, and no longer blinding in dark mode - toast notification about newly opened background tabs in frameless mode (can be disabled in settings) - redesigned the infobar, it no longer looks out of place - improved QR code generation, now it's actually useful - downloads bubble is now shown instead of the full page whenever applicable - kagi search now supports reverse image search from image context menu - frameless mode animations are now smoother - better color contrast in light and dark modes - a lot of bug fixes and other minor improvements all of these changes are present in the latest version of helium. if you're using helium on windows, please update to the latest version, so your browser can be updated automatically from now on!

Helium

109,004 görüntüleme • 1 ay önce

Another week of shipping at Atlas! Excited to share these with you: - Save prompts that you use frequently and access them anywhere with @ and in the bookmarks bar - Rename your tabs - Device tab in Dev Tools so you can see how websites respond on different devices - Smarter transition between agent mode/chat so you are not stuck in the wrong mode - Bug fixes across autofill, extensions, side chat suggestions, and picture-in-picture Just hit the update button on the top right to get the latest goodies.
0:29

Another week of shipping at Atlas! Excited to share these with you: - Save prompts that you use frequently and access them anywhere with @ and in the bookmarks bar - Rename your tabs - Device tab in Dev Tools so you can see how websites respond on different devices - Smarter transition between agent mode/chat so you are not stuck in the wrong mode - Bug fixes across autofill, extensions, side chat suggestions, and picture-in-picture Just hit the update button on the top right to get the latest goodies.

James Sun

20,700 görüntüleme • 5 ay önce

<weverse live 140725> 🐥 back then, i didn’t want to grow old or for my appearance to change. i just wanted to stay in this appearance with all of you for a very long time 🐥 but now, rather than thinking only about getting older, -c [1/2]
0:36

<weverse live 140725> 🐥 back then, i didn’t want to grow old or for my appearance to change. i just wanted to stay in this appearance with all of you for a very long time 🐥 but now, rather than thinking only about getting older, -c [1/2]

💌

164,776 görüntüleme • 1 yıl önce

AT LAST! Custom Status Lines are coming to Codex 🙌 This is just one of many highly requested features in the pipeline. You can now run /statusline to configure exactly what shows in your terminal. Choose from 15 data points, toggle them on/off, or even reorder them. One thing I'd love to see in the future is to be able to install custom extensions that would allow you to customize their styling or run custom scripts (like weather updates). More updates coming soon, but this is the most mature imminent release (0.99 Alpha). Codex team is absolutely cooking.
0:29

AT LAST! Custom Status Lines are coming to Codex 🙌 This is just one of many highly requested features in the pipeline. You can now run /statusline to configure exactly what shows in your terminal. Choose from 15 data points, toggle them on/off, or even reorder them. One thing I'd love to see in the future is to be able to install custom extensions that would allow you to customize their styling or run custom scripts (like weather updates). More updates coming soon, but this is the most mature imminent release (0.99 Alpha). Codex team is absolutely cooking.

am.will

38,800 görüntüleme • 5 ay önce

I’m usually skeptical of “AI workspace” products, but Bloome has a few ideas I actually like: You can put humans + multiple agents in the same conversation. One agent can draft something, another can poke holes in it, and another can clean up the final version. You can also bring in different agents/models like Claude, ChatGPT, DeepSeek, etc. instead of constantly bouncing between tabs. And because the whole conversation stays in context, teammates can join later and still understand how the work got to the final output. It also works across web, desktop, and mobile, though if you’re using it for real work, I’d especially recommend trying the desktop app. Feels closer to how real teams actually work.
0:44

I’m usually skeptical of “AI workspace” products, but Bloome has a few ideas I actually like: You can put humans + multiple agents in the same conversation. One agent can draft something, another can poke holes in it, and another can clean up the final version. You can also bring in different agents/models like Claude, ChatGPT, DeepSeek, etc. instead of constantly bouncing between tabs. And because the whole conversation stays in context, teammates can join later and still understand how the work got to the final output. It also works across web, desktop, and mobile, though if you’re using it for real work, I’d especially recommend trying the desktop app. Feels closer to how real teams actually work.

AI Breakfast

78,285 görüntüleme • 20 gün önce

It’s 2;30 a.m. The music is winding down, chairs are going up on tables, and the bartender pulls up the screen showing five open tabs. The customers had left without closing out, so she shrugs, turns the tablet toward the camera, and says, “If you walk out, I’m adding 20%,” before entering the tips herself. Now, the video is circulating online, and people are split. Some say she earned it for dealing with a packed bar all night. Others say adding her own tip without consent is crossing the line. I get the frustration, serving all night and then chasing down unpaid tabs is exhausting. But transparency matters. Clear signage or an automatic gratuity policy posted in advance would protect both the staff and the customers. What do you think? If customers leave without closing their tabs, is it fair game for the bartender to add a standard 20% tip, or should there be a different policy in place?
1:01

It’s 2;30 a.m. The music is winding down, chairs are going up on tables, and the bartender pulls up the screen showing five open tabs. The customers had left without closing out, so she shrugs, turns the tablet toward the camera, and says, “If you walk out, I’m adding 20%,” before entering the tips herself. Now, the video is circulating online, and people are split. Some say she earned it for dealing with a packed bar all night. Others say adding her own tip without consent is crossing the line. I get the frustration, serving all night and then chasing down unpaid tabs is exhausting. But transparency matters. Clear signage or an automatic gratuity policy posted in advance would protect both the staff and the customers. What do you think? If customers leave without closing their tabs, is it fair game for the bartender to add a standard 20% tip, or should there be a different policy in place?

Dr. CZ

3,576,149 görüntüleme • 5 ay önce

it really doesnt matter if your agent uses the cli or mcp what really matters is how to best enable ur agents to build autonomously for u without the crossmint cli tool my agent would have to use the browser and get my input in every step. now i just let it run see how i do it
3:18

it really doesnt matter if your agent uses the cli or mcp what really matters is how to best enable ur agents to build autonomously for u without the crossmint cli tool my agent would have to use the browser and get my input in every step. now i just let it run see how i do it

joyce

14,133 görüntüleme • 5 ay önce

THIS GUY ADDED A LIVE BROWSER TO CLAUDE CODE SO YOU CAN CLICK ANY ELEMENT AND EDIT IT INSTANTLY biggest issue with vibe coding UI is that you have to describe what you want to change. if you prompt it the wrong selector or wrong component, Claude can't find it. now you just click it. your app runs in an embedded browser with Claude Code. you can click any button, any text, any div. Claude instantly knows exactly what you're pointing at. click. instruct. done. no more "change the button in the top right corner of the second card component." all you have to do now is just click the button. AND its open source
0:40

THIS GUY ADDED A LIVE BROWSER TO CLAUDE CODE SO YOU CAN CLICK ANY ELEMENT AND EDIT IT INSTANTLY biggest issue with vibe coding UI is that you have to describe what you want to change. if you prompt it the wrong selector or wrong component, Claude can't find it. now you just click it. your app runs in an embedded browser with Claude Code. you can click any button, any text, any div. Claude instantly knows exactly what you're pointing at. click. instruct. done. no more "change the button in the top right corner of the second card component." all you have to do now is just click the button. AND its open source

Om Patel

152,845 görüntüleme • 3 ay önce