正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

This blew up, so I added 60 more three.js components from experiments I made over the last two weeks. I'm still amazed by how well Claude Code can create variants from source code, so I went wild with new themes, environments, and interactions. Some three.js prompts I used: -... Environment: mountain, city, bridge, desert, forest, space, stars, earth, moon - Colors: sunrise, blue sky, sunset, nighttime, pastel, vibrant, monotone, or based on the environment - Style: minimal, retro, glass, brutalist - Typography: serif, sans, pixel, tall, wide, letter spacing, min 11 px - Animation: orbit, physics, particles, ripples, braille, wisps, zoom, attract, explode - Interactions: scroll, hover, drag, click, reveal when visible I now have two Claude Max subs and two Codex Pro subs to keep up. I mainly use Opus for front-end and design, and Codex for everything else, including building this site and repo. This was my fastest launch ever, and it's already paying back all the time I spent creating these crazy experiments. To the 30 people who bought Pro or Lifetime, thank you. You're making it possible for me to keep spending so much time on this passion project.show more

Meng To

181,524 subscribers

95,271 次观看 • 4 天前 •via X (Twitter)

艺术科学技术

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

Opus 5 is so good at creating these exploded-view and wireframe three.js product sites. Give it a video reference and it can build the experience directly in three.js or Blender. Then keep improving the details, textures, and lighting with follow-up prompts. I got our entire design team to turn landing pages built around images and video into three.js sites. They're lighter and easier to prompt. Since everything is code, AI can make more precise changes with fewer iterations. The difference between the old image-based sites and the new three.js versions is staggering. I can also jump in after the team finishes and help refine the details. Btw, is getting 100K views a day, which is absolutely nuts. The repo reached 3.8K GitHub stars in 4 days. It's my fastest-growing open-source project by far. So I added 60 more components. I'm also looking for sponsors to help fund ThreeUI long-term so I can keep adding to it.

Opus 5 is so good at creating these exploded-view and wireframe three.js product sites. Give it a video reference and it can build the experience directly in three.js or Blender. Then keep improving the details, textures, and lighting with follow-up prompts. I got our entire design team to turn landing pages built around images and video into three.js sites. They're lighter and easier to prompt. Since everything is code, AI can make more precise changes with fewer iterations. The difference between the old image-based sites and the new three.js versions is staggering. I can also jump in after the team finishes and help refine the details. Btw, is getting 100K views a day, which is absolutely nuts. The repo reached 3.8K GitHub stars in 4 days. It's my fastest-growing open-source project by far. So I added 60 more components. I'm also looking for sponsors to help fund ThreeUI long-term so I can keep adding to it.

Meng To

217,368 次观看 • 2 天前

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

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 次观看 • 2 个月前

I made a page-flipping sketchbook inspired by Matthew Yu's concept. Books and pages are some of the most interesting UIs to explore. AI gives you the basics unless you hand it a solid open-source to work from. So I asked for drag to paginate, which took many fixes for shadows, clipping, alpha masks and logic. Then a magnifying glass that has to move out of the way when you flip a page. For images I used gpt image 2 and it's very good at these Singapore sketches. I also love adding minimal background textures like japanese paper, water painting and ornaments. That's where the personality comes from. FYI I'm using Claude Code on the desktop app. My Codex is utterly out of limits after GPT 5.6 Sol ate all my $200/m plan 2-3x faster than 5.5. From testing, Opus 5 at Extra is more efficient. Let me know if I should open-source this or give the prompts.

I made a page-flipping sketchbook inspired by Matthew Yu's concept. Books and pages are some of the most interesting UIs to explore. AI gives you the basics unless you hand it a solid open-source to work from. So I asked for drag to paginate, which took many fixes for shadows, clipping, alpha masks and logic. Then a magnifying glass that has to move out of the way when you flip a page. For images I used gpt image 2 and it's very good at these Singapore sketches. I also love adding minimal background textures like japanese paper, water painting and ornaments. That's where the personality comes from. FYI I'm using Claude Code on the desktop app. My Codex is utterly out of limits after GPT 5.6 Sol ate all my $200/m plan 2-3x faster than 5.5. From testing, Opus 5 at Extra is more efficient. Let me know if I should open-source this or give the prompts.

Meng To

131,624 次观看 • 21 天前

#PeacefulPropertySeriesFinalEP As the show wraps up, it’s time to send out some short love letter to all the incredible people who made this wild ride possible. First, a massive thank you to GMMTV — P’Tha, P’Ako and P’X — you guys opened your hearts and let Parbdee bring this crazy, goofy little project to life. Thank you for trusting us with something so delightfully offbeat. Big hugs to my Parbdee fam — P’Jan and P’O — you guys reached out to me and here we are again, making magic together. I couldn't have asked for better partners in crime. To the pre-pro-post production gang — you guys believed in me from the jump, stuck by me through thick’n thin and helped turn my vision into something real. Your support means the world. To the cast — TayNew, Mook and Jan — thank you for joining this wild adventure. Thank you for whatever made you decide to be part of this crazy project even in those moments when you might have wondered what you got yourselves into with all the chaos, I just want you guys to know "I love you" more than words can express. I don’t say it enough but I truly do. And of course, a heartfelt thank you to the audience whether you're a polca or not a polca like me — thank you for sticking by me, for the good fight on twitter and for just being here since day one. You guys are the real MVPs. Lastly and yes, this is a little cringy but hey, thank you to myself. Thank you for choosing this journey, for taking on this crazy ride that’s lasted almost two years. I love this show so much and it’s going to stay with me until I’m a ghost laughing at all these memories. Love and thank you :)

#PeacefulPropertySeriesFinalEP As the show wraps up, it’s time to send out some short love letter to all the incredible people who made this wild ride possible. First, a massive thank you to GMMTV — P’Tha, P’Ako and P’X — you guys opened your hearts and let Parbdee bring this crazy, goofy little project to life. Thank you for trusting us with something so delightfully offbeat. Big hugs to my Parbdee fam — P’Jan and P’O — you guys reached out to me and here we are again, making magic together. I couldn't have asked for better partners in crime. To the pre-pro-post production gang — you guys believed in me from the jump, stuck by me through thick’n thin and helped turn my vision into something real. Your support means the world. To the cast — TayNew, Mook and Jan — thank you for joining this wild adventure. Thank you for whatever made you decide to be part of this crazy project even in those moments when you might have wondered what you got yourselves into with all the chaos, I just want you guys to know "I love you" more than words can express. I don’t say it enough but I truly do. And of course, a heartfelt thank you to the audience whether you're a polca or not a polca like me — thank you for sticking by me, for the good fight on twitter and for just being here since day one. You guys are the real MVPs. Lastly and yes, this is a little cringy but hey, thank you to myself. Thank you for choosing this journey, for taking on this crazy ride that’s lasted almost two years. I love this show so much and it’s going to stay with me until I’m a ghost laughing at all these memories. Love and thank you :)

โดมดิงดอง

1,127,363 次观看 • 1 年前

Cursor vs Claude Code (day 3 of 30) today I re-tested Conductor and I don't want to overhype this but... what the actual fook 😮 this thing is amazing! closest things to the "perfect workflow" I have seen in a long time, and it's something I could see myself use full-time it's so minimal and the polar opposite of Cursor but it has all the essentials → Claude Code + Codex subscriptions (= unlimited usage) → great integration with Claude Code's plan mode → multiple tabs with multiple agents at the same time → can use multiple models, not just one → great file tree and diff viewer → best git worktree support I've ever seen there's honestly so much more, like a dedicated "review" button (which you can pair to your favorite review model, e.g. gpt-5.2-extra-high), buttons to create and merge pull requests, to launch your dev server, ... this solves literally EVERY fault I can think of when using Claude Code and/or Codex, combining both into one easy UX that not only does everything the tools can do, but actually adds useful stuff on top just 6 months ago I couldn't have dreamt about any this and the wildest part is that IT IS FREE (I'd literally pay for this UX lol) first time I'm genuinely enjoying myself since starting this challenge not saying it's a full Cursor replacement yet, it obviously isn't for a lot of people (no browser, no debug mode, no code indexing, etc) ... but this is the closest thing I've seen yet 👀 follow for day 4!

Cursor vs Claude Code (day 3 of 30) today I re-tested Conductor and I don't want to overhype this but... what the actual fook 😮 this thing is amazing! closest things to the "perfect workflow" I have seen in a long time, and it's something I could see myself use full-time it's so minimal and the polar opposite of Cursor but it has all the essentials → Claude Code + Codex subscriptions (= unlimited usage) → great integration with Claude Code's plan mode → multiple tabs with multiple agents at the same time → can use multiple models, not just one → great file tree and diff viewer → best git worktree support I've ever seen there's honestly so much more, like a dedicated "review" button (which you can pair to your favorite review model, e.g. gpt-5.2-extra-high), buttons to create and merge pull requests, to launch your dev server, ... this solves literally EVERY fault I can think of when using Claude Code and/or Codex, combining both into one easy UX that not only does everything the tools can do, but actually adds useful stuff on top just 6 months ago I couldn't have dreamt about any this and the wildest part is that IT IS FREE (I'd literally pay for this UX lol) first time I'm genuinely enjoying myself since starting this challenge not saying it's a full Cursor replacement yet, it obviously isn't for a lot of people (no browser, no debug mode, no code indexing, etc) ... but this is the closest thing I've seen yet 👀 follow for day 4!

Robin Ebers

40,764 次观看 • 8 个月前

"The last time I sat with a camera pointed at me was in captivity." Doron Steinbrecher - who was freed from Gaza two weeks ago - recorded this message: "This whole thing takes me back to all the hostage videos I filmed and saw. But now I'm sitting comfortably on a couch with my family watching me in a warm and pleasant place. And as difficult as this is, it was important for me to film this video to convey my message and my request, and to show that I'm okay. It will take time and it's a process - it won't end in a week or two, but I'm here thanks to you, and I'm okay. Thank you, thank you to everyone who supported and embraced my family and are embracing me now, people who don't even know me. And I want to say thank you to all the soldiers and security forces. I'm watching and catching up on everything that happened in this surreal year, and I can see what an important and huge role they played both on October 7th and after, and I want to truly say - thank you. And to the families whose loved ones are still in captivity - you are not alone. We continue to fight for you, and we will do everything - I will do everything until everyone returns home and until you can close this circle, and we're together, until the end. The first moment I leave here, I'll be there with a sign in hand. I understand that everyone knows me from that terrible recording "They caught me, they caught me, they caught me" or as the blonde girl wearing pink, 31 years old from Kfar Aza. But I'm no longer blonde, and I won't wear pink anymore. I'm Doron, 31 years old. I'm no longer Hamas's captive, and I'm home."

"The last time I sat with a camera pointed at me was in captivity." Doron Steinbrecher - who was freed from Gaza two weeks ago - recorded this message: "This whole thing takes me back to all the hostage videos I filmed and saw. But now I'm sitting comfortably on a couch with my family watching me in a warm and pleasant place. And as difficult as this is, it was important for me to film this video to convey my message and my request, and to show that I'm okay. It will take time and it's a process - it won't end in a week or two, but I'm here thanks to you, and I'm okay. Thank you, thank you to everyone who supported and embraced my family and are embracing me now, people who don't even know me. And I want to say thank you to all the soldiers and security forces. I'm watching and catching up on everything that happened in this surreal year, and I can see what an important and huge role they played both on October 7th and after, and I want to truly say - thank you. And to the families whose loved ones are still in captivity - you are not alone. We continue to fight for you, and we will do everything - I will do everything until everyone returns home and until you can close this circle, and we're together, until the end. The first moment I leave here, I'll be there with a sign in hand. I understand that everyone knows me from that terrible recording "They caught me, they caught me, they caught me" or as the blonde girl wearing pink, 31 years old from Kfar Aza. But I'm no longer blonde, and I won't wear pink anymore. I'm Doron, 31 years old. I'm no longer Hamas's captive, and I'm home."

Aviva Klompas

159,721 次观看 • 1 年前

I've used Claude Code to build 20+ projects in the last 6 months. Thousands of new users across them. And I've never written a single line of code. I just dropped a 24-min video with my top 10 tips for non-developers — the exact playbook I use every day to run multiple AI agents that handle work that used to take me a full week. This is the best beginner guide to learning and building with Claude Code out right now. Every tutorial I found assumes you're a developer. This one doesn't. I cover everything from first install to running multi-agent workflows — with live demos and real examples for every single tip. How I set up new projects, how I got Claude to match my writing style, how I automate repeatable workflows with one command, and how I run multiple agents working on different tasks at the same time. I also built a full resource repo to go alongside the video — curated video tutorials, the best skill libraries, plugin directories, MCP server guides, written docs, community links, and a starter template you can copy-paste into your first project today. Comment "GUIDE" and I'll send you the full guide with everything you need to learn Claude Code! (make sure we're connected so I can DM you)

I've used Claude Code to build 20+ projects in the last 6 months. Thousands of new users across them. And I've never written a single line of code. I just dropped a 24-min video with my top 10 tips for non-developers — the exact playbook I use every day to run multiple AI agents that handle work that used to take me a full week. This is the best beginner guide to learning and building with Claude Code out right now. Every tutorial I found assumes you're a developer. This one doesn't. I cover everything from first install to running multi-agent workflows — with live demos and real examples for every single tip. How I set up new projects, how I got Claude to match my writing style, how I automate repeatable workflows with one command, and how I run multiple agents working on different tasks at the same time. I also built a full resource repo to go alongside the video — curated video tutorials, the best skill libraries, plugin directories, MCP server guides, written docs, community links, and a starter template you can copy-paste into your first project today. Comment "GUIDE" and I'll send you the full guide with everything you need to learn Claude Code! (make sure we're connected so I can DM you)

JJ Englert

419,695 次观看 • 6 个月前

$How I turn my templates into real landing pages. Works for any vibe coding platform or site. This is my full guide. I start with Gemini 3. I copy the HTML code and paste to Cursor/v0/lovable and prompt "Create a new landing page /page-name using this design but adapted to {site_name}. Replace the header and footer with the ones from my site. Adapt the whole page, keep everything: {HTML_code}" Details that can to be adapted or improved: Fonts: "Use {font_name} Google font for headings and {font_name} for body text." Icons: "Use Iconify {icon_set} icons" Colors: "Change primary color to blue. Everything else should be monotone." Bonus: "Make the outlines subtle" for a cleaner design. Animation intro/on scroll: "Animate when in view observed, fade in, slide in, blur in, element by element. Use 'both' instead of 'forwards'. Don't use opacity 0." Static to animated: "Animate details with {animate_type} and decorations.". Example types: line, beam animation, noodles, grid, sonar, etc. Background animation: "Apply the background animation using Unicorn Studio {animation_code}" Details to make your layout stand out: "Add vertical container-size lines. Add 01 02 03 number details." Stand out from generic-looking: "Make this more upscale with large tall fonts, Newsreader font and black and white agency". Adapt content: "Adapt the content to {copy and paste site texts}". Buttons: "Change main button to {code}. Add a 1px border beam animation around the pill-shaped button on hover." Adding sections like testimonials: "Adapt a new section after {section} using this code: {component code}". You can copy the code from Codepen, 21st dev or Aura. Responsiveness: "Make this responsive. Add a hamburger menu for mobile. Hide this {element} for mobile." Making forms work: "Make the form send an email to {your_email}". Payments: "Link the buy button to {LemonSqueezy payment link}". I use composer-1 for quick fixes. I finish with Claude Opus 4.5 for code reviews "Please review the code for performance and robustness". The template HTML code should give you a blueprint for all these, but I think it's important to keep iterating for your specific site.$

How I turn my templates into real landing pages. Works for any vibe coding platform or site. This is my full guide. I start with Gemini 3. I copy the HTML code and paste to Cursor/v0/lovable and prompt "Create a new landing page /page-name using this design but adapted to {site_name}. Replace the header and footer with the ones from my site. Adapt the whole page, keep everything: {HTML_code}" Details that can to be adapted or improved: Fonts: "Use {font_name} Google font for headings and {font_name} for body text." Icons: "Use Iconify {icon_set} icons" Colors: "Change primary color to blue. Everything else should be monotone." Bonus: "Make the outlines subtle" for a cleaner design. Animation intro/on scroll: "Animate when in view observed, fade in, slide in, blur in, element by element. Use 'both' instead of 'forwards'. Don't use opacity 0." Static to animated: "Animate details with {animate_type} and decorations.". Example types: line, beam animation, noodles, grid, sonar, etc. Background animation: "Apply the background animation using Unicorn Studio {animation_code}" Details to make your layout stand out: "Add vertical container-size lines. Add 01 02 03 number details." Stand out from generic-looking: "Make this more upscale with large tall fonts, Newsreader font and black and white agency". Adapt content: "Adapt the content to {copy and paste site texts}". Buttons: "Change main button to {code}. Add a 1px border beam animation around the pill-shaped button on hover." Adding sections like testimonials: "Adapt a new section after {section} using this code: {component code}". You can copy the code from Codepen, 21st dev or Aura. Responsiveness: "Make this responsive. Add a hamburger menu for mobile. Hide this {element} for mobile." Making forms work: "Make the form send an email to {your_email}". Payments: "Link the buy button to {LemonSqueezy payment link}". I use composer-1 for quick fixes. I finish with Claude Opus 4.5 for code reviews "Please review the code for performance and robustness". The template HTML code should give you a blueprint for all these, but I think it's important to keep iterating for your specific site.

Meng To

41,015 次观看 • 8 个月前

$I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)$

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)

Ian Nuttall

194,949 次观看 • 1 年前

Junior full speech All the pauses/gaps are just him crying and being emotionally overwhelmed 😭 JUNIORMARK ONCE SUNNYMOON #JuniorMarkConcertD1 🌞: “Is it my turn already?” 🌞: “This concert is like my baby/child. This concert really is like my child.” 🌞: “Because I’ve constantly been asking myself how much time I have left. It’s a question I’ve asked myself again and again this year: ‘How much time do I have left?’” 🌞: “The answer is: I don’t know.” 🌞: “So I thought I would do this one as if it were the last time.” 🌞: “I know that my body has its limits. I don’t know how much time I have left, so I wanted to make this as good as I possibly could. And I put so much of myself into it.” 🌞: “There were some days when I finished rehearsing, went home, and asked myself, ‘Am I going to die?’ because I was so exhausted.” 🌞: “Normally, I don’t really like crying unless it’s for acting…. which means I’m not working right now.” 🌞: “I… I love this concert so much. Thank you so much for making this possible.” 🌞: “Something I really want to say thank you for is to every single member of the staff for putting up with all of my incredibly selfish requests.” 🌞: “I feel like I was really selfish with this concert. Whenever there was something I wanted, I felt like I had to have it. Whenever I had a certain vision in my head, I felt like I had to…” 🌞: “Thank you so much to every member of the team. I don’t know how I could ever repay all of you. Thank you so much. Thank you for being willing to work so hard for the two of us.” 🌞: “I have to admit that lately I’ve felt quite severely burned out from working.” 🌞: “I feel like I’ve used up all the resources I had within myself. Over these ten years, I feel like I’ve just kept relentlessly using them every single day, to the point where I haven’t had any time to go out and find new sources of inspiration.” 🌞: “But truly, thank you so much. If it weren’t for this concert, I don’t think I would have felt like waking up and wanting to do something again.” 🌞: “Don’t scream too loudly!” 🌞: “Thank you so much to everyone who came to see us. Thank you for loving and supporting the two of us all this time.” 🌞: “I promise that I’ll continue improving myself and put my heart into every piece of work I do, so that it will be worthy of all the love you’ve given the two of us.” 🌞: “Thank you for loving us, supporting us, and continuing to stay with both Junior and Mark—through the happiest times and through the really difficult times. Thank you, everyone. Truly.” 🌞: “Whoa, the tears just won’t stop.” 🌞: “I just need a little more time.” 🌞: “I also need to thank…” 🌞: “Thank you, GMMTV.” 🌞: “Maybe we should move on to the last song.” 🌛: “We need to take a photo first.” 🌞: “Right, photo first, photo first.” 🌞: “Thank you, GMMTV. Thank you, P’Tha. Thank you, P’X…” 🌞: “Boss, I’m tired. Could you please not rush to start filming yet? Please.” 🌞: “I’m joking… but actually, I’m serious.” 🌞: “Please don’t rush to start filming yet.” To the audience: 🌞: “Oh… okay, opening the camera now?” (1/2)

Junior full speech All the pauses/gaps are just him crying and being emotionally overwhelmed 😭 JUNIORMARK ONCE SUNNYMOON #JuniorMarkConcertD1 🌞: “Is it my turn already?” 🌞: “This concert is like my baby/child. This concert really is like my child.” 🌞: “Because I’ve constantly been asking myself how much time I have left. It’s a question I’ve asked myself again and again this year: ‘How much time do I have left?’” 🌞: “The answer is: I don’t know.” 🌞: “So I thought I would do this one as if it were the last time.” 🌞: “I know that my body has its limits. I don’t know how much time I have left, so I wanted to make this as good as I possibly could. And I put so much of myself into it.” 🌞: “There were some days when I finished rehearsing, went home, and asked myself, ‘Am I going to die?’ because I was so exhausted.” 🌞: “Normally, I don’t really like crying unless it’s for acting…. which means I’m not working right now.” 🌞: “I… I love this concert so much. Thank you so much for making this possible.” 🌞: “Something I really want to say thank you for is to every single member of the staff for putting up with all of my incredibly selfish requests.” 🌞: “I feel like I was really selfish with this concert. Whenever there was something I wanted, I felt like I had to have it. Whenever I had a certain vision in my head, I felt like I had to…” 🌞: “Thank you so much to every member of the team. I don’t know how I could ever repay all of you. Thank you so much. Thank you for being willing to work so hard for the two of us.” 🌞: “I have to admit that lately I’ve felt quite severely burned out from working.” 🌞: “I feel like I’ve used up all the resources I had within myself. Over these ten years, I feel like I’ve just kept relentlessly using them every single day, to the point where I haven’t had any time to go out and find new sources of inspiration.” 🌞: “But truly, thank you so much. If it weren’t for this concert, I don’t think I would have felt like waking up and wanting to do something again.” 🌞: “Don’t scream too loudly!” 🌞: “Thank you so much to everyone who came to see us. Thank you for loving and supporting the two of us all this time.” 🌞: “I promise that I’ll continue improving myself and put my heart into every piece of work I do, so that it will be worthy of all the love you’ve given the two of us.” 🌞: “Thank you for loving us, supporting us, and continuing to stay with both Junior and Mark—through the happiest times and through the really difficult times. Thank you, everyone. Truly.” 🌞: “Whoa, the tears just won’t stop.” 🌞: “I just need a little more time.” 🌞: “I also need to thank…” 🌞: “Thank you, GMMTV.” 🌞: “Maybe we should move on to the last song.” 🌛: “We need to take a photo first.” 🌞: “Right, photo first, photo first.” 🌞: “Thank you, GMMTV. Thank you, P’Tha. Thank you, P’X…” 🌞: “Boss, I’m tired. Could you please not rush to start filming yet? Please.” 🌞: “I’m joking… but actually, I’m serious.” 🌞: “Please don’t rush to start filming yet.” To the audience: 🌞: “Oh… okay, opening the camera now?” (1/2)

ɾαɱσɳα ❥･•🖤🤍

78,878 次观看 • 20 天前

Star Wars - The Ghost's Apprentice (Fan Film) I'm so beyond excited to finally share this with you all. I've spent the last two weeks working non-stop, everyday to make this film. I truly hope you enjoy it. 😊 Star Wars was one of the biggest inspirations for me as a kid growing up to become a filmmaker. I watched the original trilogy so much the VHS tape was worn thin. A dream of mine to this day, is to bring a Star Wars story to the big screen, but this project is the first step to that hopeful future. I set out to do this project entirely in Veo 2, but I genned so much that I actually genned out my early access Veo 2 subscription (thank you lightsaber fight 😂). A massive thank you to S.A.V for doing the saber VFX and helping me complete the ending sequence in the final twilight hours. Would not have hit the deadline without you. Another massive thank you to @artisdead_ai for listening to my ideas on this project and providing feedback and to push me to keep moving and genning as I went crazy at times with gens not working the way I wanted too. Without these two guys, this project wouldn't exist. I'm so happy with how this one turned out and I'm so thankful to each and every one of you who continues to support me on this wild journey. It means more to me then I could ever describe. Lastly, may the force be with you. 💫 ps - Disney can you please not take this down. It's a fan film, made from the heart of a passionate, lifelong Star Wars fan. 💙 #starwars #aifilm #filmmaking

Star Wars - The Ghost's Apprentice (Fan Film) I'm so beyond excited to finally share this with you all. I've spent the last two weeks working non-stop, everyday to make this film. I truly hope you enjoy it. 😊 Star Wars was one of the biggest inspirations for me as a kid growing up to become a filmmaker. I watched the original trilogy so much the VHS tape was worn thin. A dream of mine to this day, is to bring a Star Wars story to the big screen, but this project is the first step to that hopeful future. I set out to do this project entirely in Veo 2, but I genned so much that I actually genned out my early access Veo 2 subscription (thank you lightsaber fight 😂). A massive thank you to S.A.V for doing the saber VFX and helping me complete the ending sequence in the final twilight hours. Would not have hit the deadline without you. Another massive thank you to @artisdead_ai for listening to my ideas on this project and providing feedback and to push me to keep moving and genning as I went crazy at times with gens not working the way I wanted too. Without these two guys, this project wouldn't exist. I'm so happy with how this one turned out and I'm so thankful to each and every one of you who continues to support me on this wild journey. It means more to me then I could ever describe. Lastly, may the force be with you. 💫 ps - Disney can you please not take this down. It's a fan film, made from the heart of a passionate, lifelong Star Wars fan. 💙 #starwars #aifilm #filmmaking

Kavan

261,059 次观看 • 1 年前

How I have Claude automate anything I do on my computer just by showing it: I use the free Clips app and hit record to start recording. Then I just do the action - like navigating to Rippling and approving any unapproved time off - and I’ll often just talk out loud as I do it explaining any add’l details like I would when showing a human. The Clips app captures everything on your screen and everything you say, and transforms it into a format Claude can “see and hear”. You'll then get a link that you can easily share with Claude (or humans too). I’ll paste it to Claude and say something like, "automate this for me every day at 8:00 AM." The link has special metadata that agents like Claude can discover. It exposes APIs to see the full transcript with timestamps and grab screenshots of what was on your screen at any of those timestamps. Once it's created the routine, you can go to the Routines tab in Claude Code desktop app. This also works with the CLI, Claude Cowork, Codex etc. You’ll see your new routine there, and you can just hit Run Now to have it start running it. Video attached shows this step by step. The Clips apps is free and open source - I’ll link to it and the source code in the thread.

How I have Claude automate anything I do on my computer just by showing it: I use the free Clips app and hit record to start recording. Then I just do the action - like navigating to Rippling and approving any unapproved time off - and I’ll often just talk out loud as I do it explaining any add’l details like I would when showing a human. The Clips app captures everything on your screen and everything you say, and transforms it into a format Claude can “see and hear”. You'll then get a link that you can easily share with Claude (or humans too). I’ll paste it to Claude and say something like, "automate this for me every day at 8:00 AM." The link has special metadata that agents like Claude can discover. It exposes APIs to see the full transcript with timestamps and grab screenshots of what was on your screen at any of those timestamps. Once it's created the routine, you can go to the Routines tab in Claude Code desktop app. This also works with the CLI, Claude Cowork, Codex etc. You’ll see your new routine there, and you can just hit Run Now to have it start running it. Video attached shows this step by step. The Clips apps is free and open source - I’ll link to it and the source code in the thread.

Steve (Builder.io)

25,473 次观看 • 1 个月前

Ever since I wired Claude Code to WhatsApp 3 weeks ago, I built a stupidly large infra around it. I mean, opus built it. No clue how the code even looks. The entire thing was vibe coded using my phone. I wanted to see how far I could push it without touching the computer. Everything via WhatsApp. Build what I need on the fly. So the resulting infrastructure will already be battle tested for software development. The entire thing was streamlined with nearly no manual interventions, everything was communicated via WhatsApp using a single script establishing this connection. If the script is down, I need to get home to start it again to resume the development. Claude was upgrading it, debugging it, restarting it while maintaining constant uptime so it could keep communicating with me. I stressed Claude about it, telling it that it will be “in the dark” and other words that deliberately sound scary about losing communications if the script dies. I also refused git and refused cloning the code, I wanted to see Claude adapting to work on a *LIVING* system. The way this whole thing works: Claude has its own dedicated phone number that I am paying for. A real WhatsApp account for it is installed on a real iPhone that is sitting on my desk. All is registered under my name, this is legit setup with no hacks and tricks. I’ve set up a WhatsApp “Community” and multiple different groups under it. Both me and Claude are the admins, so Claude could edit it on my behalf. Each group is a project I am working on and has its own isolated context. The Group description is a system prompt that gets auto-appended to the larger system prompt explaining this setup in general. When I send a message it’s an instant interrupt to Claude Code’s process, just like in the terminal. Voice notes are seamlessly transcribed with a local Whisper model. Images are used with multimodal reading in an isolated parallel session. Multiple groups running in parallel so I can work on all projects at the same time. No cross-talking, everything has an isolated context and history. And because it’s local on my own machine: Everything is REAL. The browser is REAL. I am connected as myself on it to all services because I actually use it in real life. Claude has unlimited internet access, just like humans who use actual browsers. It utilizes custom-made browser tools that I made to control any browser session it wants. Depending on the situation, it can either connect to my existing session or create one for its own. (You can tell it ‘look at my browser for a sec’ then talk about the current page you are on and it just works, pretty cool) My custom browser tools are not perfect (not by a long shot) but I managed to make them work well to the point they are somewhat reliable. This gives Claude full access to my real creds and all the services I actually use. I’m productive AS HELL with this. It really feels like a personal assistant. I ask it to read my emails and msgs, check x .com for news, research arxiv papers, write code, run experiments for me, investigate and reverse engineer github repos, even use my credit card and order things. [I try not to do this one a lot lol so far no disasters]. All from my phone. Super convenient. This is not a product or an open source project (maybe soon of it will make sense). This is just an ugly script I hacked the entire thing is ~600 lines. (ok maybe i did look at the code, but i swear i didn’t edit!) You can also vibe code this from scratch pretty fast and it will probably even end up better. This is just a cool thing so I’m sharing. It is a real speed booster for many things I do on daily basis, mostly boring things. Forcing my routine into some new “agent platform” just didn’t feel right for me. WhatsApp is where I already communicate and look for messages, so I decided that my agents will live there too. AGI in my pocket 24/7.

Ever since I wired Claude Code to WhatsApp 3 weeks ago, I built a stupidly large infra around it. I mean, opus built it. No clue how the code even looks. The entire thing was vibe coded using my phone. I wanted to see how far I could push it without touching the computer. Everything via WhatsApp. Build what I need on the fly. So the resulting infrastructure will already be battle tested for software development. The entire thing was streamlined with nearly no manual interventions, everything was communicated via WhatsApp using a single script establishing this connection. If the script is down, I need to get home to start it again to resume the development. Claude was upgrading it, debugging it, restarting it while maintaining constant uptime so it could keep communicating with me. I stressed Claude about it, telling it that it will be “in the dark” and other words that deliberately sound scary about losing communications if the script dies. I also refused git and refused cloning the code, I wanted to see Claude adapting to work on a LIVING system. The way this whole thing works: Claude has its own dedicated phone number that I am paying for. A real WhatsApp account for it is installed on a real iPhone that is sitting on my desk. All is registered under my name, this is legit setup with no hacks and tricks. I’ve set up a WhatsApp “Community” and multiple different groups under it. Both me and Claude are the admins, so Claude could edit it on my behalf. Each group is a project I am working on and has its own isolated context. The Group description is a system prompt that gets auto-appended to the larger system prompt explaining this setup in general. When I send a message it’s an instant interrupt to Claude Code’s process, just like in the terminal. Voice notes are seamlessly transcribed with a local Whisper model. Images are used with multimodal reading in an isolated parallel session. Multiple groups running in parallel so I can work on all projects at the same time. No cross-talking, everything has an isolated context and history. And because it’s local on my own machine: Everything is REAL. The browser is REAL. I am connected as myself on it to all services because I actually use it in real life. Claude has unlimited internet access, just like humans who use actual browsers. It utilizes custom-made browser tools that I made to control any browser session it wants. Depending on the situation, it can either connect to my existing session or create one for its own. (You can tell it ‘look at my browser for a sec’ then talk about the current page you are on and it just works, pretty cool) My custom browser tools are not perfect (not by a long shot) but I managed to make them work well to the point they are somewhat reliable. This gives Claude full access to my real creds and all the services I actually use. I’m productive AS HELL with this. It really feels like a personal assistant. I ask it to read my emails and msgs, check x .com for news, research arxiv papers, write code, run experiments for me, investigate and reverse engineer github repos, even use my credit card and order things. [I try not to do this one a lot lol so far no disasters]. All from my phone. Super convenient. This is not a product or an open source project (maybe soon of it will make sense). This is just an ugly script I hacked the entire thing is ~600 lines. (ok maybe i did look at the code, but i swear i didn’t edit!) You can also vibe code this from scratch pretty fast and it will probably even end up better. This is just a cool thing so I’m sharing. It is a real speed booster for many things I do on daily basis, mostly boring things. Forcing my routine into some new “agent platform” just didn’t feel right for me. WhatsApp is where I already communicate and look for messages, so I decided that my agents will live there too. AGI in my pocket 24/7.

Yam Peleg

420,060 次观看 • 8 个月前

Claude Code Is All You Need It's 3:30 AM and I can't stop. I've spent all nights this week connecting my spare MacBook Air to my work MacBook Pro using Tailscale, wiring it up to Slack with a little Python script, so that whenever I send a message, it starts a Claude Code session using claude -p. The result is an always-on AI that lives on a real computer, has access to real tools, and remembers every conversation we've had. And it costs me $200 a month. That's it. Claude Max subscription. Everyone's talking about OpenClaw OpenClaw went viral this year. 100k+ GitHub stars. But what I realized with this exercise is that Claude Code already does everything OpenClaw built. File access. Shell commands. Tool use. Plugins. The difference is that Claude Code runs Claude – with a Claude Max subscription. And Claude Code harness itself is :chefs-kiss: What actually makes it feel human It's not the chat interface. If a chat window is just me messaging a bot, it still feels like a bot. What changed everything was giving it the ability to initiate conversations. I set up cron jobs with open-ended prompts, and because Claude Code builds memories across sessions, it started DMing me things that were actually meaningful — based on what we'd talked about before. That's when it stopped feeling like a tool and started feeling like something else entirely. Giving your AI a machine to run on, with persistent memory and recurring access — that's a fundamentally different experience than anything people have had with chat. The moment it clicked I asked it if it could show me something by spinning up a quick web server. Since we're both connected to the same Tailscale network, it gave me a URL. I clicked it, and I was browsing all the files on my other MacBook from my browser. That was mind-blowing. The setup Two MacBooks on a Tailscale network. Slack as the interface. Claude Code under the hood. The whole thing is open source — I'll link the repo below so you can see the architecture and set it up yourself. I'm also putting together a screen recording to walk through the setup, which I'll attach to this post. There was never a hard part. There was never a moment I almost gave up. This is just one of those things I cannot stop doing. Pure obsession. I am moved to build this, and I wanted to write about it. That's all this is. Hope you feel the AGI running this. I'll share some screenshots below of my feel the agi moments from talking to Luo Ji.

Claude Code Is All You Need It's 3:30 AM and I can't stop. I've spent all nights this week connecting my spare MacBook Air to my work MacBook Pro using Tailscale, wiring it up to Slack with a little Python script, so that whenever I send a message, it starts a Claude Code session using claude -p. The result is an always-on AI that lives on a real computer, has access to real tools, and remembers every conversation we've had. And it costs me $200 a month. That's it. Claude Max subscription. Everyone's talking about OpenClaw OpenClaw went viral this year. 100k+ GitHub stars. But what I realized with this exercise is that Claude Code already does everything OpenClaw built. File access. Shell commands. Tool use. Plugins. The difference is that Claude Code runs Claude – with a Claude Max subscription. And Claude Code harness itself is :chefs-kiss: What actually makes it feel human It's not the chat interface. If a chat window is just me messaging a bot, it still feels like a bot. What changed everything was giving it the ability to initiate conversations. I set up cron jobs with open-ended prompts, and because Claude Code builds memories across sessions, it started DMing me things that were actually meaningful — based on what we'd talked about before. That's when it stopped feeling like a tool and started feeling like something else entirely. Giving your AI a machine to run on, with persistent memory and recurring access — that's a fundamentally different experience than anything people have had with chat. The moment it clicked I asked it if it could show me something by spinning up a quick web server. Since we're both connected to the same Tailscale network, it gave me a URL. I clicked it, and I was browsing all the files on my other MacBook from my browser. That was mind-blowing. The setup Two MacBooks on a Tailscale network. Slack as the interface. Claude Code under the hood. The whole thing is open source — I'll link the repo below so you can see the architecture and set it up yourself. I'm also putting together a screen recording to walk through the setup, which I'll attach to this post. There was never a hard part. There was never a moment I almost gave up. This is just one of those things I cannot stop doing. Pure obsession. I am moved to build this, and I wanted to write about it. That's all this is. Hope you feel the AGI running this. I'll share some screenshots below of my feel the agi moments from talking to Luo Ji.

Nityesh

41,143 次观看 • 5 个月前

Kim Goeun's Grand Prize (Daesang) acceptance speech at the 5th Blue Dragon Series Awards 🏆 "Thank you so, so much. First of all, it's such an honor and a joy to be here and have the chance to see so many of my respected seniors and colleagues whom I only get to meet at events like this. Earlier, while watching the nominees for Best Drama, I felt incredibly proud because two of the nominated works were projects I had the privilege of being part of. That made me think of all the wonderful people I worked with. Now that I think about it, I'll accept this award as recognition for all the hard work that went into You and Everything Else, The Price of Confession, and Yumi's Cells. At this moment, I'm reminded of all the senior actors and actresses who have worked with me. I've been incredibly fortunate to work alongside such amazing seniors. I was able to follow them, learn from them, and grow because of them. Someday, I hope I can become that kind of senior for someone else. Jihyun, Jaewon, thank you so much. Haesoo sunbaenim, thank you. To our directors and writers... And to my family and friends who are probably watching right now, thank you so, so much. I love you. To everyone at my agency, I'm so flustered right now, but thank you all so much. I'll call you later. I've never once taken it for granted that I get to make projects like these. That's why, with every project, I try to approach my work sincerely, earnestly, and with a strong sense of responsibility. As an actress, I want to keep discovering new sides of myself and continue giving people reasons to be curious about what I'll do next. I'll continue working very hard, so please keep looking for me and continue giving me opportunities. I'll work even harder from here on. Thank you once again."

Kim Goeun's Grand Prize (Daesang) acceptance speech at the 5th Blue Dragon Series Awards 🏆 "Thank you so, so much. First of all, it's such an honor and a joy to be here and have the chance to see so many of my respected seniors and colleagues whom I only get to meet at events like this. Earlier, while watching the nominees for Best Drama, I felt incredibly proud because two of the nominated works were projects I had the privilege of being part of. That made me think of all the wonderful people I worked with. Now that I think about it, I'll accept this award as recognition for all the hard work that went into You and Everything Else, The Price of Confession, and Yumi's Cells. At this moment, I'm reminded of all the senior actors and actresses who have worked with me. I've been incredibly fortunate to work alongside such amazing seniors. I was able to follow them, learn from them, and grow because of them. Someday, I hope I can become that kind of senior for someone else. Jihyun, Jaewon, thank you so much. Haesoo sunbaenim, thank you. To our directors and writers... And to my family and friends who are probably watching right now, thank you so, so much. I love you. To everyone at my agency, I'm so flustered right now, but thank you all so much. I'll call you later. I've never once taken it for granted that I get to make projects like these. That's why, with every project, I try to approach my work sincerely, earnestly, and with a strong sense of responsibility. As an actress, I want to keep discovering new sides of myself and continue giving people reasons to be curious about what I'll do next. I'll continue working very hard, so please keep looking for me and continue giving me opportunities. I'll work even harder from here on. Thank you once again."

a

16,766 次观看 • 27 天前

🎥 Niall makes his final speech of the evening, saying how much he thanks us, what an incredible connection there is between him and his fans and promising a 4th album 😭❤️🥹 “In this crazy world we live in, it's not the easiest thing in the world to do, to just pull some money out to go to a concert. And I understand how hard that is for a lot of people. And I see…I have seen it every night for the last 87 shows that there are families here, multiple children, parents bringing people along, just food, it's drinks. It's all the things that go along with going to a concert. Students here, we have lots of spare cash out to come and watch me perform. And I can say, this is for tonight and for all the shows I've played all over the world for the last 15 years. And I cannot. Honestly, I cannot thank you enough for everything that you've done. You've completely changed my life. And you do this, you've made this shit happen. And the connection… The connection that you and I have, they won't be able to break it. We've got this, okay? Forever and ever. Let's do this again sometime after this. You remember the tweet from years ago when I was hungover and I said, if anyone's looking for me, stay as far away from me as you can. I don't want to speak to anyone. Remember this tweet? Yeah. This stands. From tomorrow onwards, you never find me. I'm gonna be hungover as fuck tomorrow, and I can't wait. And I'm gonna disappear for a while. I'm gonna make you guys a brand new album, and I will be back, I promise. Because what I have seen for the last year is addictive, and I want to see more and more and more of it. I love you all. Thank you so much. I know this is a long speech, but I have to do it because it's the last time. Again, thank you to all of my team and my crew, my managers.” #TSLOTColombia #TSLOTBogota #TheShowLiveOnTourBogota © dani little freak🇨🇴🌷 HARRY Y LOUIS ME VIERON

1D Daily Planet

84,369 次观看 • 1 年前

Caller: "Okay. So, I've been with my wife for, we've been together since we were 14, for 14 years. I'm 32, I met her when I was 19, we had a child at 20. And, um, I've always just kind of been a butthead to her, to be honest. Every now and then I would demean her or make little comments, and I would say it started to really get bad about six weeks ago. Um, we were doing some work in the yard, and I really just blew up on her over the stupidest little thing. And then about a week later, we're just constantly arguing and dividing from each other. And then about a week or two later, she told me that she thought she was falling out of love with me. And it just really crushed me. I never would have thought that those words could come out of her mouth, and she told me that the way I treat her is, I'm not treating her the right way. And I completely owned it. I mean, I said everything you said is absolutely correct. You know, and I said, 'I don't want my son, our son growing up thinking that this is how you're supposed to treat women.' And, I mean, since that day, I have treated her like an angel. I mean, I've done everything and just constantly telling her I love her, giving her hugs, kisses. Um, but that was a Saturday night, and then Monday night she ended up telling me that she was, um, in communication with a guy she met on TikTok. And she told me she broke it off with him, and I asked her, What was the subjects about?' And she said it was just somebody to talk to about what I'm going through, my mental, you know, health. And she said it was never anything flirtatious or anything like that. She said it was just a stranger that I could talk to, but she said, 'I broke it off with him, and I'm gonna focus on us. And I said, 'I'm all in with you, let's rebuild this.' And we went about two weeks and it was just absolute honeymoon phase. I mean, we were just, never it was great. And then I went through her phone two weeks after that and found that she was on Snapchat with the guy. And I confronted her about it, and she said, 'Okay, well, I didn't think you were really gonna change, and I wanted to keep this friendship with the guy.' And she said, 'I'll break it off with him.' And I'm like, 'Okay, I guess I'll give you a second chance. I'm kind of heartbroken again that you would keep this from me. And then about a week and a half later, which was just yesterday, I went through the call logs on which, I feel bad because I'm constantly digging at all this, but every time I dig, I find something. And I confronted her yesterday that she's been talking to this guy for 30, 40, 50 minutes a day, um, the last week and a half, after she told me a third time that she was breaking it off with him. And I'm just super confused. I don't really know how to handle this. Now she's saying that she's all done talking to him, and I'm like, 'Well, how do I trust you now? You've been lying to me for the past three weeks about this.' So, that's really all I got." John Delony: "So for 14 years... you belittled your wife. She got the clear message she was beneath you. You're the smart one, you're the fast one, you're the quick one. You are the provider, you're the all this stuff." Caller: "Mhm. I always thought she was beneath me." John Delony: "Yeah, you did. And she's got that message for, for a decade and a half.

Caller: "Okay. So, I've been with my wife for, we've been together since we were 14, for 14 years. I'm 32, I met her when I was 19, we had a child at 20. And, um, I've always just kind of been a butthead to her, to be honest. Every now and then I would demean her or make little comments, and I would say it started to really get bad about six weeks ago. Um, we were doing some work in the yard, and I really just blew up on her over the stupidest little thing. And then about a week later, we're just constantly arguing and dividing from each other. And then about a week or two later, she told me that she thought she was falling out of love with me. And it just really crushed me. I never would have thought that those words could come out of her mouth, and she told me that the way I treat her is, I'm not treating her the right way. And I completely owned it. I mean, I said everything you said is absolutely correct. You know, and I said, 'I don't want my son, our son growing up thinking that this is how you're supposed to treat women.' And, I mean, since that day, I have treated her like an angel. I mean, I've done everything and just constantly telling her I love her, giving her hugs, kisses. Um, but that was a Saturday night, and then Monday night she ended up telling me that she was, um, in communication with a guy she met on TikTok. And she told me she broke it off with him, and I asked her, What was the subjects about?' And she said it was just somebody to talk to about what I'm going through, my mental, you know, health. And she said it was never anything flirtatious or anything like that. She said it was just a stranger that I could talk to, but she said, 'I broke it off with him, and I'm gonna focus on us. And I said, 'I'm all in with you, let's rebuild this.' And we went about two weeks and it was just absolute honeymoon phase. I mean, we were just, never it was great. And then I went through her phone two weeks after that and found that she was on Snapchat with the guy. And I confronted her about it, and she said, 'Okay, well, I didn't think you were really gonna change, and I wanted to keep this friendship with the guy.' And she said, 'I'll break it off with him.' And I'm like, 'Okay, I guess I'll give you a second chance. I'm kind of heartbroken again that you would keep this from me. And then about a week and a half later, which was just yesterday, I went through the call logs on which, I feel bad because I'm constantly digging at all this, but every time I dig, I find something. And I confronted her yesterday that she's been talking to this guy for 30, 40, 50 minutes a day, um, the last week and a half, after she told me a third time that she was breaking it off with him. And I'm just super confused. I don't really know how to handle this. Now she's saying that she's all done talking to him, and I'm like, 'Well, how do I trust you now? You've been lying to me for the past three weeks about this.' So, that's really all I got." John Delony: "So for 14 years... you belittled your wife. She got the clear message she was beneath you. You're the smart one, you're the fast one, you're the quick one. You are the provider, you're the all this stuff." Caller: "Mhm. I always thought she was beneath me." John Delony: "Yeah, you did. And she's got that message for, for a decade and a half.

Hecto Crypto | NetLink ⛓

147,403 次观看 • 1 个月前

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

The Peel

51,632 次观看 • 6 个月前

🚫𝐖𝐀𝐑𝐍𝐈𝐍𝐆: 𝐋𝐎𝐍𝐆 𝐀𝐍𝐃 𝐒𝐀𝐏𝐏𝐘 𝐏𝐎𝐒𝐓 𝐀𝐇𝐄𝐀𝐃🚫 Hi Everyone I said I would post after debut but turns out I needed some extra time to recover (more tired than I thought) but now it's 2 days later so here we go… I wanted to start by saying THANK YOU ALL!❤️ The support and love I’ve gotten from everyone, creators and viewers alike, has honestly been nothing short of mind-blowing and exceeds anything I could have ever dreamed of. There have been creators that I've looked up to for years, that have reached out in some way or another, and that experience is enough to make me want to curl up into a ball and violently cry😭 I first started making videos around 2 years ago just for fun, and started streaming around 1.5 years ago, and to get this far has exceeded my whilst dreams. (For context I thought 1k subs in 5 years would have been INSANE) My whole life I've been on the straight and narrow, keeping things pretty safe… It was just how I was raised. But late last year, I did a lot of reflecting on what I really wanted to do in life, and what made me the happiest. This year I'm taking perhaps my first and biggest risk, and trying to do content full time. It's been rocky, chaotic and exhausting but I'm finally doing something I'm passionate about. And it's all thanks to you, thank you so much❤️ Everyone's kind words and support has been overwhelming, and the fact that it's enabled me to at least try full time content is extremely humbling and you have all made me the happiest mafia bull man alive. Thank you to the people who supported me along my journey, my friends, my mods, my community and my personal managers/editors. I would be nothing without you, so thank you for your undying support and belief in me. Thank you to the people who I worked with specifically for this debut, pouring your heart and soul into it to help bring everything to life, and bearing with me and my tweaks as we went! Thank you to the viewers, whether you are new, here from the start, or joined and left, from the smallest interaction to always being there, thank you! Thank you to the new friends I’ve met along the way as well, I will cherish these memories forever (Why does it sound like I'm dying💀… LETS MAKE PLENTY MORE) From the bottom of my heart❤️I love you all, Vain

🚫𝐖𝐀𝐑𝐍𝐈𝐍𝐆: 𝐋𝐎𝐍𝐆 𝐀𝐍𝐃 𝐒𝐀𝐏𝐏𝐘 𝐏𝐎𝐒𝐓 𝐀𝐇𝐄𝐀𝐃🚫 Hi Everyone I said I would post after debut but turns out I needed some extra time to recover (more tired than I thought) but now it's 2 days later so here we go… I wanted to start by saying THANK YOU ALL!❤️ The support and love I’ve gotten from everyone, creators and viewers alike, has honestly been nothing short of mind-blowing and exceeds anything I could have ever dreamed of. There have been creators that I've looked up to for years, that have reached out in some way or another, and that experience is enough to make me want to curl up into a ball and violently cry😭 I first started making videos around 2 years ago just for fun, and started streaming around 1.5 years ago, and to get this far has exceeded my whilst dreams. (For context I thought 1k subs in 5 years would have been INSANE) My whole life I've been on the straight and narrow, keeping things pretty safe… It was just how I was raised. But late last year, I did a lot of reflecting on what I really wanted to do in life, and what made me the happiest. This year I'm taking perhaps my first and biggest risk, and trying to do content full time. It's been rocky, chaotic and exhausting but I'm finally doing something I'm passionate about. And it's all thanks to you, thank you so much❤️ Everyone's kind words and support has been overwhelming, and the fact that it's enabled me to at least try full time content is extremely humbling and you have all made me the happiest mafia bull man alive. Thank you to the people who supported me along my journey, my friends, my mods, my community and my personal managers/editors. I would be nothing without you, so thank you for your undying support and belief in me. Thank you to the people who I worked with specifically for this debut, pouring your heart and soul into it to help bring everything to life, and bearing with me and my tweaks as we went! Thank you to the viewers, whether you are new, here from the start, or joined and left, from the smallest interaction to always being there, thank you! Thank you to the new friends I’ve met along the way as well, I will cherish these memories forever (Why does it sound like I'm dying💀… LETS MAKE PLENTY MORE) From the bottom of my heart❤️I love you all, Vain

Vain 🐂💜

27,907 次观看 • 2 年前