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。

⚡ My first advanced simulation with Grok 3! Finally your OS windows act like REAL windows 🤣 As you know, I've spent more than 2 years sharing all kinds of simulations and mini-games made with Claude, ChatGPT (o3-mini-high), etc. It’s been ages since I last wrote a single line... of code. But pretty often, once you hit over 1,000 lines, it turns into a debate against the LLM and you frequently get stuck in a loop that’s hard to break out of. Everyone was raving about Grok 3’s ability to generate code, but until now, I hadn’t really put it to the test. So I decided to challenge it with a prompt that both ChatGPT and Claude were seriously struggling with (debate loop). The initial prompt was: "Use Python and a 2D physics library to create a world where I can generate different static objects like squares, triangles, circles and rectangles. I should be able to move them with the mouse, rotate, scale, and delete them. The cool part is that we’ll see this world through 1 to N operating system windows. In other words, the windows will be like real windows! When one of these windows is active and I hit the spacebar, balls affected by physics should appear and interact with the static objects. You can start with placeholders, but later I'll send you a series of PNG images so they all become beautiful sprites." After a few iterations, I got the result you see in the video. Insane, right? 🤯 Now, with Grok, we have the power to create anything that pops into our mind with just a couple of prompts. It’s mind blowing. Ever since I was 9 and messing around with BASIC on my MSX, I've been hooked on visual simulations... And now I can create them using nothing but natural language. It's f***** amazing that we're living in this historic moment!show more

Javi Lopez ⛩️

126,143 subscribers

209,470 次观看 • 1 年前 •via X (Twitter)

游戏科学技术教育

Anya Rossi• Live Now

Private livecam show

11 条评论

Javi Lopez ⛩️ 的头像

Javi Lopez ⛩️1 年前

It all started like this! What a time to be alive 🤯

Javi Lopez ⛩️ 的头像

Javi Lopez ⛩️1 年前

I generated all the sprites and backgrounds using Magnific's Mystic Fluid/Flexible with prompts like: - "New Super Mario Bros 2D platform videogame screenshot, full of impressive wooden boxes of all forms and shapes" - "New Super Mario Bros 2D platform videogame screenshot, full of impressive colorful clouds" I simply cropped them in Photoshop, made the background transparent, and saved them as PNGs.

Javi Lopez ⛩️ 的头像

Javi Lopez ⛩️1 年前

Other simulation I’ve made and you may enjoy:

Javi Lopez ⛩️ 的头像

Javi Lopez ⛩️1 年前

And a mini game (almost 2 years ago already. Time flies!). I have to make more mini games :)

Javi Lopez ⛩️ 的头像

Javi Lopez ⛩️1 年前

Maybe you're wondering if the image I showed before was from the real Mario or just generated... It was generated!!! Proof: And soon, we’ll have directly playable worlds just from a prompt. I think we’ll be there in less than 2 years!

Javi Lopez ⛩️ 的头像

Javi Lopez ⛩️1 年前

This is sooooo much fun. I think this simulation could eventually become a mini game too! :) Any ideas to improve / add some game mechanics to it?

Javi Lopez ⛩️ 的头像

Javi Lopez ⛩️1 年前

CC @elonmusk

OPEN 的头像

OPEN1 年前

OP3N delivers the ultimate gaming experience with no limits. Wishlist now and be one of the first to dive into the excitement of the new game!

Nuclear Samurai 的头像

Nuclear Samurai1 年前

i have been in so many AI code debate loops over the last two years it is crazy, i'm so glad that some models are finally breaking free from these loops

Javi Lopez ⛩️ 的头像

Javi Lopez ⛩️1 年前

"Can you please, pleaaaaase, read the newest implementation of this library and stop inventing functions. You m**** f*****!!!!"

🍓 的头像

🍓1 年前

Source code please

相关视频

Pi was built when there were already agent harnesses around. Here’s why Mario Zechner(Mario Zechner), found them suboptimal and built Pi, a minimalist self-modifying agent: #1 - Mario initially was a believer in Claude Code: "I was a believer in Claude code because they were the first that packaged agentic search up in a really compelling package. And at the time that fit my workflow really well. Everything around the LLM was kind of nice and tidy and easy to understand. I was super happy. I was proselytising Claude code." #2 - Reverse engineering Claude Code highlighted the degradation that Mario felt as a user: "I personally like simple tools that are stable and that I can rely on. Even if they have non-deterministic parts, all the deterministic parts should be as stable as possible. That was just not the experience with Claude Code around summer 2025. They would take away your control of the context. They would inject stuff behind your back, which is bad. Then, your workflows stopped working because there's now a system reminder that you don't even see in the UI that would modify the behaviour of the model. They would also do this to the system prompt. I built a little service where I can track the progression or evolution of the system, prompt and tool definitions and, with every release, it was messing with stuff. That just messed with my workflows and I don't appreciate that." #3 - PI was built with an appreciation for simple and reliable tools: "If I commit to a development tool, I want it to be a stable, reliable thing like a hammer. I don't want my hammer to break a different spot every day. That's terrible. We need somebody who goes the full velocity kind of way. But I don't want to work with a tool like that."

Pi was built when there were already agent harnesses around. Here’s why Mario Zechner(Mario Zechner), found them suboptimal and built Pi, a minimalist self-modifying agent: #1 - Mario initially was a believer in Claude Code: "I was a believer in Claude code because they were the first that packaged agentic search up in a really compelling package. And at the time that fit my workflow really well. Everything around the LLM was kind of nice and tidy and easy to understand. I was super happy. I was proselytising Claude code." #2 - Reverse engineering Claude Code highlighted the degradation that Mario felt as a user: "I personally like simple tools that are stable and that I can rely on. Even if they have non-deterministic parts, all the deterministic parts should be as stable as possible. That was just not the experience with Claude Code around summer 2025. They would take away your control of the context. They would inject stuff behind your back, which is bad. Then, your workflows stopped working because there's now a system reminder that you don't even see in the UI that would modify the behaviour of the model. They would also do this to the system prompt. I built a little service where I can track the progression or evolution of the system, prompt and tool definitions and, with every release, it was messing with stuff. That just messed with my workflows and I don't appreciate that." #3 - PI was built with an appreciation for simple and reliable tools: "If I commit to a development tool, I want it to be a stable, reliable thing like a hammer. I don't want my hammer to break a different spot every day. That's terrible. We need somebody who goes the full velocity kind of way. But I don't want to work with a tool like that."

The Pragmatic Engineer

63,088 次观看 • 6 个月前

💾 Okay I finally bought a Raspberry Pi 5 to make into a real retro computer as a proof of concept I love the Raspberry Pi much more than my ESP32 simply because I can SSH into it and it's just like a normal computer or server, the ESP32 required specific software to re-flash it everytime and it was TEDIOUS!!!! I need a fast feedback loop to develop with so all this flashing is too slow for me The Raspberry Pi 5 instead just runs Linux which then runs DOSBox-X to run Windows 3.11 install live downloaded from there so it stays fresh I then also got a Checkmate 19" IPS Retro Monitor by Stephen Jones (very indie and Kickstarter-style product) which is like a vintage retro PC monitor but with an OLED and it runs at 1280x1024, and the Raspberry Pi 5 has HDMI out so it works perfectly with it Then I got an 8BitDo retro IBM keyboard, but the spacebar broke, so I gotta send it back and get a new one, but it was great while it worked, so it's not in this video, and I got the 8BitDo retro mouse So altogether it's a proof of concept of a real vintage retro PC with internet and it works now My end goal is to make this into production and SELL it, not for money but more for fun because I think it should exist, just like Palmer Luckey's ModRetro Chromatic Gameboy-remake I'd go with something smaller than this 19" checkmate display though, it's great but too big for the Windows 3.11 era I think, more like 14" with a matching sized retro IBM-style keyboard and Windows 3.11 preinstalled (if legally allowed by Satya Nadella) with WiFi working out of the box We could also go with Windows 98/XP, because for me too Windows 3.11 was a very short time, so I too have vague memories of it, most of my computing memories is Windows 98/XP etc. Inside it could simply run on a Raspberry Pi 5 like here, which is easily powerful enough to run all of these OS'es I see many SF founders with Apple II's in their living room, and I guess cause Apple was more popular there back then, but in the rest of the world we were mostly IBM PCs and clones that ran Windows, so it's cool to have that as one retro object working with internet in your living room Anyway, step by step, we're here now 😊

💾 Okay I finally bought a Raspberry Pi 5 to make into a real retro computer as a proof of concept I love the Raspberry Pi much more than my ESP32 simply because I can SSH into it and it's just like a normal computer or server, the ESP32 required specific software to re-flash it everytime and it was TEDIOUS!!!! I need a fast feedback loop to develop with so all this flashing is too slow for me The Raspberry Pi 5 instead just runs Linux which then runs DOSBox-X to run Windows 3.11 install live downloaded from there so it stays fresh I then also got a Checkmate 19" IPS Retro Monitor by Stephen Jones (very indie and Kickstarter-style product) which is like a vintage retro PC monitor but with an OLED and it runs at 1280x1024, and the Raspberry Pi 5 has HDMI out so it works perfectly with it Then I got an 8BitDo retro IBM keyboard, but the spacebar broke, so I gotta send it back and get a new one, but it was great while it worked, so it's not in this video, and I got the 8BitDo retro mouse So altogether it's a proof of concept of a real vintage retro PC with internet and it works now My end goal is to make this into production and SELL it, not for money but more for fun because I think it should exist, just like Palmer Luckey's ModRetro Chromatic Gameboy-remake I'd go with something smaller than this 19" checkmate display though, it's great but too big for the Windows 3.11 era I think, more like 14" with a matching sized retro IBM-style keyboard and Windows 3.11 preinstalled (if legally allowed by Satya Nadella) with WiFi working out of the box We could also go with Windows 98/XP, because for me too Windows 3.11 was a very short time, so I too have vague memories of it, most of my computing memories is Windows 98/XP etc. Inside it could simply run on a Raspberry Pi 5 like here, which is easily powerful enough to run all of these OS'es I see many SF founders with Apple II's in their living room, and I guess cause Apple was more popular there back then, but in the rest of the world we were mostly IBM PCs and clones that ran Windows, so it's cool to have that as one retro object working with internet in your living room Anyway, step by step, we're here now 😊

@levelsio

155,824 次观看 • 1 年前

Zack Snyder on his dyslexia: "It was a challenge for me when I was, you know, young in school, and all I wanted to do was make movies because that was the thing that I got great pleasure from and reward from. I love books, and I'm an avid reader, but I just have a hard time because of the way that I perceive. "I've had a great sort of - one side of me anyways - was really satisfied by art and drawing and sculpture and sort of visual expression. And I think that that started to, you know, was the thing that kind of made me feel un-frustrated. And also the way the system was designed, sort of not to support me when I was in high school at that time. "It was very difficult, you know, there was a lot of, you know, just, difficulty. My English teacher in high school was worried about what my career would be, and I'm like. He would be happy to know that I'm in the Writers Guild of America now. "But, I think that that all those things are, they're all... you can transcend all those things with perseverance and with interest and with with help. And I think that that's an important part of it. "And I just think I've had to adapt, and sort of... I have my own style of the way I write, I write all, you know, but I'm pretty prolific. And I love- I listen to tons of audio books on tape, unabridged hours and hours and hours. That's all I do when I'm driving in the car or wherever I'm doing. And it's helped me a lot. "And yeah, I mean, I just hope that anyone who is- feels trapped or frustrated by the world in general. You know, they need to just, I think that we all have like a magic spark, and you need to just find the thing that makes you, you know, inspires you and, and gets you excited and pursue it as hard as you can find your passion in the world. That's a, that's a great motivator."

Zack Snyder on his dyslexia: "It was a challenge for me when I was, you know, young in school, and all I wanted to do was make movies because that was the thing that I got great pleasure from and reward from. I love books, and I'm an avid reader, but I just have a hard time because of the way that I perceive. "I've had a great sort of - one side of me anyways - was really satisfied by art and drawing and sculpture and sort of visual expression. And I think that that started to, you know, was the thing that kind of made me feel un-frustrated. And also the way the system was designed, sort of not to support me when I was in high school at that time. "It was very difficult, you know, there was a lot of, you know, just, difficulty. My English teacher in high school was worried about what my career would be, and I'm like. He would be happy to know that I'm in the Writers Guild of America now. "But, I think that that all those things are, they're all... you can transcend all those things with perseverance and with interest and with with help. And I think that that's an important part of it. "And I just think I've had to adapt, and sort of... I have my own style of the way I write, I write all, you know, but I'm pretty prolific. And I love- I listen to tons of audio books on tape, unabridged hours and hours and hours. That's all I do when I'm driving in the car or wherever I'm doing. And it's helped me a lot. "And yeah, I mean, I just hope that anyone who is- feels trapped or frustrated by the world in general. You know, they need to just, I think that we all have like a magic spark, and you need to just find the thing that makes you, you know, inspires you and, and gets you excited and pursue it as hard as you can find your passion in the world. That's a, that's a great motivator."

Zack Snyder Film

11,128 次观看 • 10 个月前

my new song “BREAKDOWN.” is out on the 21st of June!!! 🖤🖤🖤 I wrote this poem because it’s been the hardest year for my mental health. In my life I’ve always never felt good enough, it’s just the thing that’s eaten me up. For as long as I can remember i have felt constantly afraid of how quickly my head can turn dark. It’s always been so hard to fight the darkness that i inevitably have. A lot of people will say it’s a phase and it will go away. But it doesn’t and the reality of the situation is I have to find strategies to deal with it. To put it plainly the things I don’t like about myself will probably never change, people tell me one day I’ll come-to terms with them one day but I want that day to be FUCKING NOW. This song is a message to myself to try and exist alongside my insecurities and my darkness by grounding myself and remembering what is real in life and the world is so much bigger than me. Try and get out of your head and notice the world around you, notice the things and people around you. Connect with them, the chances are they probably feel the same. Don’t let the bullshit inside your head consume you. It just wastes precious time. Remember what is real. Help people, be kind, help the world, help yourself. If you think you can’t do it, you can. You can get through this, trust me. Use this poem in a mornin to get u out of bed, use it when youre about to back out of something last minute, use it when you’re at your darkest. It’s got a little bit of light in it. Don’t forget to put your feet in the grass … Mind

my new song “BREAKDOWN.” is out on the 21st of June!!! 🖤🖤🖤 I wrote this poem because it’s been the hardest year for my mental health. In my life I’ve always never felt good enough, it’s just the thing that’s eaten me up. For as long as I can remember i have felt constantly afraid of how quickly my head can turn dark. It’s always been so hard to fight the darkness that i inevitably have. A lot of people will say it’s a phase and it will go away. But it doesn’t and the reality of the situation is I have to find strategies to deal with it. To put it plainly the things I don’t like about myself will probably never change, people tell me one day I’ll come-to terms with them one day but I want that day to be FUCKING NOW. This song is a message to myself to try and exist alongside my insecurities and my darkness by grounding myself and remembering what is real in life and the world is so much bigger than me. Try and get out of your head and notice the world around you, notice the things and people around you. Connect with them, the chances are they probably feel the same. Don’t let the bullshit inside your head consume you. It just wastes precious time. Remember what is real. Help people, be kind, help the world, help yourself. If you think you can’t do it, you can. You can get through this, trust me. Use this poem in a mornin to get u out of bed, use it when youre about to back out of something last minute, use it when you’re at your darkest. It’s got a little bit of light in it. Don’t forget to put your feet in the grass … Mind

YUNGBLUD

66,954 次观看 • 2 年前

Hirokazu Koreeda on how he directs Children: "Interviewer: I think 'Shoplifters' (2018) is very remarkable in showing different sides of a city and like you said, people who are pretty much invisible, but I do want to also commend you on another thing, is you often work with young actors, and they always tend to have a significant role in many of your films. How do you go about finding such dynamic young actors, and why do you often put these young people at the center of each one of your stories? Koreeda: First of all, I would say that I tend to make what I would call family dramas, and of course, you have to have children if you’re creating a family, but that’s how it started, but I found that as I did it, I became really interested. It became very interesting and fun to work with these children, and for example, the two children in this film, neither of them had any acting experience at all before this film. I brought them in, and what I find when you bring these children in, and you work with them is that the adult actors change. They become much more lively and natural in the way that they act, and I guess, at some point, I realized this, and I guess, became really attracted to the idea of having children and the impact that it had. Interviewer: Do you find that there is any struggle in terms of working with young actors, or in this case, young children who have not actually acted before? Koreeda: Just to clarify, I have worked with children in many of my films, and all of them have never had experienced before. I always go out and pick non-acting children to work in my films, so just, I wanted to put that out there. In terms of the struggle, it does take time. You have to give extra time to work with these children. When I choose these children, I have an audition, and I pick out who I want to the audition, and then when we get to set, I never give them the script. No child that I’ve worked with has been given a script beforehand, and when I get to the actual part where they’re going to be acting, I give them the lines myself, and work with them and coach them. What I find is that it’s actually really enjoyable, both for them and for myself that way. I also, because I’ve been doing this now for several years, I tend to have a fairly high success rate in choosing children that are able to work with me in that way. Interviewer: That’s fascinating, and it also shows how you are able to create such authentic performances from these child actors over and over again in so many of your films. I think it’s a unique gift that you have, and it’s something that very few directors, I think, here in the United States do. Koreeda: It’s true, I guess by working with these children, I learned. I discovered that the best way to do it was just to communicate verbally their lines, rather than giving them in a written format, and over time, this really worked, and so I just kept doing it. But, interestingly, I loved the movie 'Kramer vs Kramer' (1979), directed by Robert Benton, and one time I bought the movie with all the extra, the making of and everything, and I went over it, and I found through that, that in fact, the child in that movie was also given his lines every day by the assistant director each morning when they came in to set, so I discovered that it wasn’t just me that was doing this." (Koreeda's interview with Scott Menzel, We Live Entertainment, 2018)

Hirokazu Koreeda on how he directs Children: "Interviewer: I think 'Shoplifters' (2018) is very remarkable in showing different sides of a city and like you said, people who are pretty much invisible, but I do want to also commend you on another thing, is you often work with young actors, and they always tend to have a significant role in many of your films. How do you go about finding such dynamic young actors, and why do you often put these young people at the center of each one of your stories? Koreeda: First of all, I would say that I tend to make what I would call family dramas, and of course, you have to have children if you’re creating a family, but that’s how it started, but I found that as I did it, I became really interested. It became very interesting and fun to work with these children, and for example, the two children in this film, neither of them had any acting experience at all before this film. I brought them in, and what I find when you bring these children in, and you work with them is that the adult actors change. They become much more lively and natural in the way that they act, and I guess, at some point, I realized this, and I guess, became really attracted to the idea of having children and the impact that it had. Interviewer: Do you find that there is any struggle in terms of working with young actors, or in this case, young children who have not actually acted before? Koreeda: Just to clarify, I have worked with children in many of my films, and all of them have never had experienced before. I always go out and pick non-acting children to work in my films, so just, I wanted to put that out there. In terms of the struggle, it does take time. You have to give extra time to work with these children. When I choose these children, I have an audition, and I pick out who I want to the audition, and then when we get to set, I never give them the script. No child that I’ve worked with has been given a script beforehand, and when I get to the actual part where they’re going to be acting, I give them the lines myself, and work with them and coach them. What I find is that it’s actually really enjoyable, both for them and for myself that way. I also, because I’ve been doing this now for several years, I tend to have a fairly high success rate in choosing children that are able to work with me in that way. Interviewer: That’s fascinating, and it also shows how you are able to create such authentic performances from these child actors over and over again in so many of your films. I think it’s a unique gift that you have, and it’s something that very few directors, I think, here in the United States do. Koreeda: It’s true, I guess by working with these children, I learned. I discovered that the best way to do it was just to communicate verbally their lines, rather than giving them in a written format, and over time, this really worked, and so I just kept doing it. But, interestingly, I loved the movie 'Kramer vs Kramer' (1979), directed by Robert Benton, and one time I bought the movie with all the extra, the making of and everything, and I went over it, and I found through that, that in fact, the child in that movie was also given his lines every day by the assistant director each morning when they came in to set, so I discovered that it wasn’t just me that was doing this." (Koreeda's interview with Scott Menzel, We Live Entertainment, 2018)

DepressedBergman

49,522 次观看 • 9 个月前

Yves via Billboard France on Instagram Reels “Back when I first started as a solo artist, I had a lot of meetings with different companies, and there were also certain perceptions from the public. I heard a lot of things like, “It’s hard to succeed as a soloist”, or “You only did well because you were in a group”. Hearing that so often really affected my self-esteem, and I think I had a strong desire to prove myself to those people. But now, I try to see those perspectives as a form of interest and accept them with gratitude. By taking in different kinds of feedback, I feel like my mindset has shifted to enjoying the process itself. I think I’m able to work with less stress and more happiness now. These days, the K-pop industry is changing very quickly, and so are the systems within entertainment companies. When I was promoting with LOONA, it felt like our role was mainly to carry out concepts that the company had already decided for us. But now, it feels like artists are much more involved and have an environment where they can actively participate and create something more creatively. When I first finished working on the song ‘NAIL’, I had already recorded the full version myself. It sounded good, but I kept thinking that if I collaborated with another artist and created synergy, the song could become even richer. The company agreed with that idea, so we started thinking about who would be a good fit to collaborate with. Around that time, we actually received a collaboration e-mail from Lolo Zouaï first. I listened to the demo she sent, and there were so many unexpected melodies that we hadn’t even imagined. In the end, we scrapped our original second verse and fully incorporated Lolo Zouaï’s demo into the track, creating the song together. Through that process, seeing how she came up with melodies we hadn’t thought of made me realize, ‘Oh, you can approach top lines like this’, and ‘You can play with rhythm in this way too’. I was able to learn a lot, and I’m really grateful for that experience”

Yves via Billboard France on Instagram Reels “Back when I first started as a solo artist, I had a lot of meetings with different companies, and there were also certain perceptions from the public. I heard a lot of things like, “It’s hard to succeed as a soloist”, or “You only did well because you were in a group”. Hearing that so often really affected my self-esteem, and I think I had a strong desire to prove myself to those people. But now, I try to see those perspectives as a form of interest and accept them with gratitude. By taking in different kinds of feedback, I feel like my mindset has shifted to enjoying the process itself. I think I’m able to work with less stress and more happiness now. These days, the K-pop industry is changing very quickly, and so are the systems within entertainment companies. When I was promoting with LOONA, it felt like our role was mainly to carry out concepts that the company had already decided for us. But now, it feels like artists are much more involved and have an environment where they can actively participate and create something more creatively. When I first finished working on the song ‘NAIL’, I had already recorded the full version myself. It sounded good, but I kept thinking that if I collaborated with another artist and created synergy, the song could become even richer. The company agreed with that idea, so we started thinking about who would be a good fit to collaborate with. Around that time, we actually received a collaboration e-mail from Lolo Zouaï first. I listened to the demo she sent, and there were so many unexpected melodies that we hadn’t even imagined. In the end, we scrapped our original second verse and fully incorporated Lolo Zouaï’s demo into the track, creating the song together. Through that process, seeing how she came up with melodies we hadn’t thought of made me realize, ‘Oh, you can approach top lines like this’, and ‘You can play with rhythm in this way too’. I was able to learn a lot, and I’m really grateful for that experience”

Yves Support

34,624 次观看 • 5 个月前

How to build a brand from scratch using Paper, Codex + GPT image model 2 Since two weeks back, I´ve done most of my design work in paper And I´m genuinely impressed by what you can do with their MCP Combined with claude & codex you can pretty much build out a brand in an hour or two 1. Brainstorm a name for you product or service 2. find a good design system you can iterate on or come up with one from scratch 3. create a moodboard of things you like and want the brand to be about (images, colors, shapes, elements, you name it) inside paper 4. select the moodboard and prompt codex to create a brand brief (hooked up to paper mcp) to create the inital brand book in code 5. Use the new brand book you created and copy as PNG, take that image into ChatGPT and use GPT model 2 (with the brand prompt) to create the brand book 6. You will get a finished and well-done 10 paged brand book Now you can use that to create anything in line with the brand: Landing pags, lead magnets, ads, anything you can think of Comment "bookmarkable" + RT and I´ll send you the brand prompt and step by step guide in DMs.

Shann³

14,592 次观看 • 6 个月前

Quick video on how I used claude code, icon composer, and my iOS app to make my app icon. I got a ton of questions about how I did it: It started with two questions: can you reshape the route to approximate a "p" more but like a character of a p not a real "p" as a test icon? "Can you give me a settings sheet where I can parametrically create The loop that I want to make... like, give me every possible parameter for the loop in the three d scene, and then make sure I can copy those values to you. And we could take that and implement it. I think that might be faster for me to be able to manipulate a p shaped loop."

Quick video on how I used claude code, icon composer, and my iOS app to make my app icon. I got a ton of questions about how I did it: It started with two questions: can you reshape the route to approximate a "p" more but like a character of a p not a real "p" as a test icon? "Can you give me a settings sheet where I can parametrically create The loop that I want to make... like, give me every possible parameter for the loop in the three d scene, and then make sure I can copy those values to you. And we could take that and implement it. I think that might be faster for me to be able to manipulate a p shaped loop."

Kris Puckett

24,429 次观看 • 3 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 • 8 个月前

This is one of the coolest open-source AI agent projects I've seen in a while: 'Understand Anything' It's a plugin for Claude Code, Codex, OpenCode etc. that analyzes your codebase and turns it into a knowledge base that you can interact with. It explains the codebase to you, rather than showing you the structure. It seems like it's designed for code but I opened my Obsidian vault of podcast highlights in Claude Code, then ran /understand. The result is a knowledge graph that I can search of highlights from 888 podcast episodes and 144K lines of markdown text.

This is one of the coolest open-source AI agent projects I've seen in a while: 'Understand Anything' It's a plugin for Claude Code, Codex, OpenCode etc. that analyzes your codebase and turns it into a knowledge base that you can interact with. It explains the codebase to you, rather than showing you the structure. It seems like it's designed for code but I opened my Obsidian vault of podcast highlights in Claude Code, then ran /understand. The result is a knowledge graph that I can search of highlights from 888 podcast episodes and 144K lines of markdown text.

Dan McAteer

175,308 次观看 • 4 个月前

Tom Holland: Rob, I'd love to chat to you about something that I've noticed that I really think you are the best in our business at doing this. I've had the pleasure of working with you three times and every time I see you take the screen, you do something with your voice. You're like a chameleon. You have an ability to change your voice without an audience watching it going, 'Oh, he's doing a voice.' For actors everywhere, how do you do that? And what's that process like? Where does that start for you? RP: I'm not really sure. I guess if you're just spending so much time reading stuff, it's like, I think, in general, one of the first things that makes me want to do a job in the first place, you're kind of, you want to say something out loud. And I think, I don't know, I think maybe it's just always because you don't know what you're doing and it's always kind of interesting when you say something. This is the first time where I've really done something where you're really trying to imitate someone's voice. In general, I remember when we were doing [The Devil All The Time] and I kept saying that I wanted, I was going to do, to Antonio, that I was going to do an MLK impression the whole time and he was like, 'But why? Why? It has nothing to do with it.' And that was my– but I kept doing it the whole time. There's something, I guess, when you can just follow, some edge, something where you can kind of be like, oh, it's something to grip onto and if it feels unusual and pleasurable to speak in, I find a lot of pleasure in trying to find a different area of your voice to use. But this was like, it was the most rigorous, conventional way of doing an accent that I'd ever done where I found it really tough. And it was one of the reasons why I couldn't, I wasn't sure about doing the movie in the first place. I found my voice notes the other day and how I was doing this voice at the beginning, because I think I must have done it the week after we met, and I was like, 'Can I do it?' And I listened to his show and tried to do it and it just sounded like, completely nothing like it. And I think I only really got it when we were rehearsing. I remember being in the car and we were looking at locations and I was like, 'Oh, that kind of sounds like it.' And I remember doing a voice memo where I was recording him saying the same line I'd been saying afterwards. I'm like, 'You can't tell the difference between the two? Yayyy!' But I don't know how. I didn't initially find that an interesting part when I first started acting. But I guess it's the easiest thing you can do by yourself until you start doing a movie and you can kind of go like, oh, I can record myself doing it and I can kind of get some kind of feedback doing it. And then you can at least, if you turn up to set, at least you've got something which you can hold on to, I think.

Tom Holland: Rob, I'd love to chat to you about something that I've noticed that I really think you are the best in our business at doing this. I've had the pleasure of working with you three times and every time I see you take the screen, you do something with your voice. You're like a chameleon. You have an ability to change your voice without an audience watching it going, 'Oh, he's doing a voice.' For actors everywhere, how do you do that? And what's that process like? Where does that start for you? RP: I'm not really sure. I guess if you're just spending so much time reading stuff, it's like, I think, in general, one of the first things that makes me want to do a job in the first place, you're kind of, you want to say something out loud. And I think, I don't know, I think maybe it's just always because you don't know what you're doing and it's always kind of interesting when you say something. This is the first time where I've really done something where you're really trying to imitate someone's voice. In general, I remember when we were doing [The Devil All The Time] and I kept saying that I wanted, I was going to do, to Antonio, that I was going to do an MLK impression the whole time and he was like, 'But why? Why? It has nothing to do with it.' And that was my– but I kept doing it the whole time. There's something, I guess, when you can just follow, some edge, something where you can kind of be like, oh, it's something to grip onto and if it feels unusual and pleasurable to speak in, I find a lot of pleasure in trying to find a different area of your voice to use. But this was like, it was the most rigorous, conventional way of doing an accent that I'd ever done where I found it really tough. And it was one of the reasons why I couldn't, I wasn't sure about doing the movie in the first place. I found my voice notes the other day and how I was doing this voice at the beginning, because I think I must have done it the week after we met, and I was like, 'Can I do it?' And I listened to his show and tried to do it and it just sounded like, completely nothing like it. And I think I only really got it when we were rehearsing. I remember being in the car and we were looking at locations and I was like, 'Oh, that kind of sounds like it.' And I remember doing a voice memo where I was recording him saying the same line I'd been saying afterwards. I'm like, 'You can't tell the difference between the two? Yayyy!' But I don't know how. I didn't initially find that an interesting part when I first started acting. But I guess it's the easiest thing you can do by yourself until you start doing a movie and you can kind of go like, oh, I can record myself doing it and I can kind of get some kind of feedback doing it. And then you can at least, if you turn up to set, at least you've got something which you can hold on to, I think.

Fansite | Robert Pattinson Photos

18,119 次观看 • 1 天前

I'm a big fan of this style, and I'm so glad I was able to create it with these dynamic 3D camera movements with Grok Imagine. I really like the result, and I hope you will too.

I'm a big fan of this style, and I'm so glad I was able to create it with these dynamic 3D camera movements with Grok Imagine. I really like the result, and I hope you will too.

Déborah

18,887 次观看 • 5 个月前

This video is the one Kim Runner shared with me in July 2024 about how to tell whether you or others are NPCs. I can vividly imagine the stickiness and feel of holding an apple in my hand, the sensation of it denting when I squeeze it hard, its smell, and even its texture. Honestly, I was greatly shocked to learn that some people cannot do this. Below is the transcript of the audio.⬇️ Have you guys seen this experiment where you can not only test if the people around you are NPCs, but if you yourself are? Check this out. And if you don't know what an NPC is, basically, in the video game world, it's someone that's not being controlled by a person, just a random computer-generated thing. And in the real world, same thing, maybe just someone that's not being controlled by a soul. So I heard this experiment on a podcast, and I thought it was kind of crazy until I tried it out myself. And it has to do with apples. And you can probably use any object, but for our purposes, we're going to stick with apples. So there are going to be multiple layers to what I'm going to ask you to imagine. And depending on how far you can imagine it might just depend on if you're an NPC or not. So with this blank screen, I want you to picture a red apple here. Can you picture a red apple? If you can, great. So far, you're not an NPC. Next, I'd like you to think of that red apple, and in your mind—you can close your eyes if you need to—think of that apple as green. Can you change it to a green apple? Can you see a green apple without looking at it? Now stick with me. We're getting to the good parts here. If you can picture a red apple and then a green apple, great, but here's where a lot of people get stuck. And I'm taking away the image here. I want you to picture that green apple in your mind, and can you go in, and can you pick up that apple? Can you manipulate it? Can you move it around? Can you in your mind be holding it, and then all of a sudden it turns from green to purple? Do you have the ability to do that? Because for me, I could, no problem. I could hold that, I could throw it, I could take a bite of it, anything I wanted to do with that apple, I could do in my mind. But the shocking part was, as I was listening to this on the podcast, one person, they were stuck. They couldn't do anything but change colors. They couldn't grab it, they couldn't manipulate it. It was stuck there. One person couldn't even change colors of the apple. But I didn't believe this until I tried it on my wife. And my wife, she could change the color—she could go green and red—but she didn't have the ability to manipulate that apple. She couldn't grab that apple, she couldn't throw that apple. I'm juggling this apple, I'm doing all sorts of things with it, but hers is just a stuck image. And I thought that was nuts. I thought just because I had the ability to manipulate things in my mind and control things, that everybody did, but clearly that's not the case. And this leads me down the path of maybe this is why some people can't grasp the topics or the understanding of not living where we've been told we live our entire lives, because they can't visualize it, they can't think outside the green and red apple. Now, I'm not actually saying my wife is an NPC, but I do think our brains operate differently. I do think some are more right, some are more left, some are right down the middle, and some just don't really choose to think. But try it out, guys, because I found it fascinating, and I would love to hear how you did during this little experiment. Put it in the comments, test it on the people around you, and let me know, cause I want to know if I'm in the majority or if I'm in the minority. But something tells me I might be in the minority. But guys, as always, this was all for entertainment purposes. I don't really think my wife is an NPC... (Female voice) Tyler, can you come here?

This video is the one Kim Runner shared with me in July 2024 about how to tell whether you or others are NPCs. I can vividly imagine the stickiness and feel of holding an apple in my hand, the sensation of it denting when I squeeze it hard, its smell, and even its texture. Honestly, I was greatly shocked to learn that some people cannot do this. Below is the transcript of the audio.⬇️ Have you guys seen this experiment where you can not only test if the people around you are NPCs, but if you yourself are? Check this out. And if you don't know what an NPC is, basically, in the video game world, it's someone that's not being controlled by a person, just a random computer-generated thing. And in the real world, same thing, maybe just someone that's not being controlled by a soul. So I heard this experiment on a podcast, and I thought it was kind of crazy until I tried it out myself. And it has to do with apples. And you can probably use any object, but for our purposes, we're going to stick with apples. So there are going to be multiple layers to what I'm going to ask you to imagine. And depending on how far you can imagine it might just depend on if you're an NPC or not. So with this blank screen, I want you to picture a red apple here. Can you picture a red apple? If you can, great. So far, you're not an NPC. Next, I'd like you to think of that red apple, and in your mind—you can close your eyes if you need to—think of that apple as green. Can you change it to a green apple? Can you see a green apple without looking at it? Now stick with me. We're getting to the good parts here. If you can picture a red apple and then a green apple, great, but here's where a lot of people get stuck. And I'm taking away the image here. I want you to picture that green apple in your mind, and can you go in, and can you pick up that apple? Can you manipulate it? Can you move it around? Can you in your mind be holding it, and then all of a sudden it turns from green to purple? Do you have the ability to do that? Because for me, I could, no problem. I could hold that, I could throw it, I could take a bite of it, anything I wanted to do with that apple, I could do in my mind. But the shocking part was, as I was listening to this on the podcast, one person, they were stuck. They couldn't do anything but change colors. They couldn't grab it, they couldn't manipulate it. It was stuck there. One person couldn't even change colors of the apple. But I didn't believe this until I tried it on my wife. And my wife, she could change the color—she could go green and red—but she didn't have the ability to manipulate that apple. She couldn't grab that apple, she couldn't throw that apple. I'm juggling this apple, I'm doing all sorts of things with it, but hers is just a stuck image. And I thought that was nuts. I thought just because I had the ability to manipulate things in my mind and control things, that everybody did, but clearly that's not the case. And this leads me down the path of maybe this is why some people can't grasp the topics or the understanding of not living where we've been told we live our entire lives, because they can't visualize it, they can't think outside the green and red apple. Now, I'm not actually saying my wife is an NPC, but I do think our brains operate differently. I do think some are more right, some are more left, some are right down the middle, and some just don't really choose to think. But try it out, guys, because I found it fascinating, and I would love to hear how you did during this little experiment. Put it in the comments, test it on the people around you, and let me know, cause I want to know if I'm in the majority or if I'm in the minority. But something tells me I might be in the minority. But guys, as always, this was all for entertainment purposes. I don't really think my wife is an NPC... (Female voice) Tyler, can you come here?

kouji 🇯🇵

122,763 次观看 • 1 个月前

Trump: They don't want any more windows. No more windows. They want to take down every building and build a building with no windows in it. I've always been known for having the biggest windows. I got, I want those windows to be so big right down to the bottom of the floor. I got to change my whole philosophy if you don't vote me in because I go back to building crazy buildings now and I won't be able to use windows anymore. No, they actually, they don't want windows, they don't want cows (???)

Trump: They don't want any more windows. No more windows. They want to take down every building and build a building with no windows in it. I've always been known for having the biggest windows. I got, I want those windows to be so big right down to the bottom of the floor. I got to change my whole philosophy if you don't vote me in because I go back to building crazy buildings now and I won't be able to use windows anymore. No, they actually, they don't want windows, they don't want cows (???)

Headquarters

1,972,922 次观看 • 2 年前

Day 18. Building the game I've dreamed of for 15 years with AI. I've learned how to build proper levels with AI. I take the design and the architecture, and AI helps me put it all together and check the balance. I made the first level of my game almost entirely by hand. I wanted to understand how it works and what I like, from how big the trees should be to how the textures tile. After a day digging around in the terrain tools it all made sense, and I could see how much of it could be automated by painting zones. Claude helped me a lot with the tileable textures. Matching the colors took a ton of iterations, and that was the hardest part of the whole level. For level two I took a different route. I built myself a simple HTML planner with a logical map of the level, where I place everything and design the layout. Painting a level and making it fun to play are two different jobs, so I kept the design for myself. We even made automated tests with Claude: 2D simulations that show which routes a player takes and how hard the level is. They're rough, but they give a real sense of how the level plays. Once the plan was ready, I handed everything to Claude, and 3-4 hours later I had a working level. It reused the patterns from my first level, scattered objects unevenly so nothing looks placed on a grid, and generated extra props whenever I asked. I showed it one example, it picked up what worked, and we turned that into a skill for the next levels. The video is a quick flight over level two, then how it got there, from my first sketch to the version I play now.

Day 18. Building the game I've dreamed of for 15 years with AI. I've learned how to build proper levels with AI. I take the design and the architecture, and AI helps me put it all together and check the balance. I made the first level of my game almost entirely by hand. I wanted to understand how it works and what I like, from how big the trees should be to how the textures tile. After a day digging around in the terrain tools it all made sense, and I could see how much of it could be automated by painting zones. Claude helped me a lot with the tileable textures. Matching the colors took a ton of iterations, and that was the hardest part of the whole level. For level two I took a different route. I built myself a simple HTML planner with a logical map of the level, where I place everything and design the layout. Painting a level and making it fun to play are two different jobs, so I kept the design for myself. We even made automated tests with Claude: 2D simulations that show which routes a player takes and how hard the level is. They're rough, but they give a real sense of how the level plays. Once the plan was ready, I handed everything to Claude, and 3-4 hours later I had a working level. It reused the patterns from my first level, scattered objects unevenly so nothing looks placed on a grid, and generated extra props whenever I asked. I showed it one example, it picked up what worked, and we turned that into a skill for the next levels. The video is a quick flight over level two, then how it got there, from my first sketch to the version I play now.

Stefan 3D AI

47,407 次观看 • 1 个月前

Companies are going way too far to try and sell you products Just to buy 2 new windows, a company came out and said you have to - Do a 3 window minimum even through you only need 2 - Sit through a 90 minute presentation on the history of the company, the founder, their story - A presentation on windows, how windows work and why their windows are different - A pitch on the state of the economy and inflation - A horrible negotiation experience on the cost of the actual windows This is actually happening at a lot of places. A similar experience of mine was I literally went to get an oil change at Mountain View tires and they wanted me to come out to the car and go over a full vehicle diagnostic that they would first need to take over an hour doing. They said it was policy It’s all to upsell you. Even places like valvoline make you do a full vehicle inspection now so they can go over it with you and upsell you on repairs

Companies are going way too far to try and sell you products Just to buy 2 new windows, a company came out and said you have to - Do a 3 window minimum even through you only need 2 - Sit through a 90 minute presentation on the history of the company, the founder, their story - A presentation on windows, how windows work and why their windows are different - A pitch on the state of the economy and inflation - A horrible negotiation experience on the cost of the actual windows This is actually happening at a lot of places. A similar experience of mine was I literally went to get an oil change at Mountain View tires and they wanted me to come out to the car and go over a full vehicle diagnostic that they would first need to take over an hour doing. They said it was policy It’s all to upsell you. Even places like valvoline make you do a full vehicle inspection now so they can go over it with you and upsell you on repairs

Wall Street Apes

106,511 次观看 • 4 个月前

Chanhyuk: Company doesn’t matter, but it’s about the people you work with. “There’s also something like this. Even though we say we created a “company,” we just used that word because it’s easier for people to understand. But in the end, it’s not really about the company, it’s about the people. Like, who you work with. And what kind of experiences you share with them, that’s what really matters the most. So with these people, whether we go, volunteering or travel somewhere, we always move together as one group. Because if not and later on, when I write and release a song, if we hadn’t shared those experiences, I’d have to explain everything. Like, “I went somewhere and had this kind of experience…” But since we’ve all lived it together, I can just say, “Hey, I wrote this kind of song this time,” and they’ll be like, “Oh, yeah, I get it. I know exactly what that is.” It just makes everything so much faster, right?”

Chanhyuk: Company doesn’t matter, but it’s about the people you work with. “There’s also something like this. Even though we say we created a “company,” we just used that word because it’s easier for people to understand. But in the end, it’s not really about the company, it’s about the people. Like, who you work with. And what kind of experiences you share with them, that’s what really matters the most. So with these people, whether we go, volunteering or travel somewhere, we always move together as one group. Because if not and later on, when I write and release a song, if we hadn’t shared those experiences, I’d have to explain everything. Like, “I went somewhere and had this kind of experience…” But since we’ve all lived it together, I can just say, “Hey, I wrote this kind of song this time,” and they’ll be like, “Oh, yeah, I get it. I know exactly what that is.” It just makes everything so much faster, right?”

akmerch ⚔️

194,390 次观看 • 7 个月前