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。

With the right agent harness you actually can start to make some interesting things. Case in point: This was made with Opus 5 in a few hours. It had to create the models, textures, quests, map, enemies, enemy AI, etc. And it had to load the game, play it,... show more

Brad Wardell

60,334 subscribers

19,778 次观看 • 21 天前 •via X (Twitter)

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

I applied Matt's prompt, ran it for a little over ten hours. About 1.3 million tokens on Opus 5. It created the game. I also made a video of it using Opus 5. Here's the video (and in my reply to this is a link to the actual game so you can play).

I applied Matt's prompt, ran it for a little over ten hours. About 1.3 million tokens on Opus 5. It created the game. I also made a video of it using Opus 5. Here's the video (and in my reply to this is a link to the actual game so you can play).

James Altucher

128,128 次观看 • 28 天前

Build furniture from oak. Stick it in an ammonia chamber. Give it a few hours. The tannins in the wood react with the ammonia and the longer you leave it in there can take the color from brown, to grey, to black. Finish it with some wax and you’re good to go.

Build furniture from oak. Stick it in an ammonia chamber. Give it a few hours. The tannins in the wood react with the ammonia and the longer you leave it in there can take the color from brown, to grey, to black. Finish it with some wax and you’re good to go.

Alex Forbes

147,114 次观看 • 3 个月前

Did you know that Visual Studio Code has HAD a built-in browser! Say "start my app in simple browser" and it will run the dev server and open simple browser to localhost. It can take screenshots of the page or element and send DOM elements to the agent chat!

Did you know that Visual Studio Code has HAD a built-in browser! Say "start my app in simple browser" and it will run the dev server and open simple browser to localhost. It can take screenshots of the page or element and send DOM elements to the agent chat!

James Montemagno

47,505 次观看 • 9 个月前

Cursor now has a built-in web browser. You can say "start my app" and it will run the dev server in a terminal and then navigate the browser to localhost:3000. It can take screenshots of the page for iterating on design, and you can send DOM elements to the agent with prompts!

Cursor now has a built-in web browser. You can say "start my app" and it will run the dev server in a terminal and then navigate the browser to localhost:3000. It can take screenshots of the page for iterating on design, and you can send DOM elements to the agent with prompts!

Lee Robinson

216,209 次观看 • 9 个月前

“We had to sit in it. We had to take it, and I think sometimes, when you sit in it [and] you’re honest with yourself and you take it, some great things can happen.” Purdue Men's Basketball Head Coach Matt Painter joined Evan Washburn postgame as Purdue advances to the Final Four⬇️

“We had to sit in it. We had to take it, and I think sometimes, when you sit in it [and] you’re honest with yourself and you take it, some great things can happen.” Purdue Men's Basketball Head Coach Matt Painter joined Evan Washburn postgame as Purdue advances to the Final Four⬇️

March Madness Men’s Basketball TV

191,226 次观看 • 2 年前

It takes 5 minutes to create a world-class web research agent that runs 24/7 and returns structured search results. 1. You can limit the sources it's allowed to use 2. You can specify the goals it needs to complete 3. You can design the format structure of the results 4. You can configure how much computing power it will use I show you how to set up a Web Search Agent in the video. A few benefits here: 1. This is great for complex research tasks 2. It's really easy to add this like a LEGO piece to a more complex workflow 3. Create an agent once, and reuse it with different inputs 4. The agent adapts to your use case as you work with it By the way, Nimble published a whole library of templates and research agents you can reuse and modify. You can start sending queries to one of these existing agents, and it will begin to adapt to Go here to try it out: Thanks to the Nimble team for partnering with me on this post.

It takes 5 minutes to create a world-class web research agent that runs 24/7 and returns structured search results. 1. You can limit the sources it's allowed to use 2. You can specify the goals it needs to complete 3. You can design the format structure of the results 4. You can configure how much computing power it will use I show you how to set up a Web Search Agent in the video. A few benefits here: 1. This is great for complex research tasks 2. It's really easy to add this like a LEGO piece to a more complex workflow 3. Create an agent once, and reuse it with different inputs 4. The agent adapts to your use case as you work with it By the way, Nimble published a whole library of templates and research agents you can reuse and modify. You can start sending queries to one of these existing agents, and it will begin to adapt to Go here to try it out: Thanks to the Nimble team for partnering with me on this post.

Santiago

20,943 次观看 • 20 天前

I have revived Javi Lopez ⛩️'s 28 year old custom map he made and made a web-based Quake 2 with Fable on fast mode 🤓 You can now play it here: 👉 👈 It took a bit of hacking because the textures didn't load the first time, so I repacked some PAK files and now it works! AI is so good at reviving old stuff from your backups, I was always waiting for some backup app to come to finally be able to browse all my old files and figure stuff out from it, and now you can with AI

I have revived Javi Lopez ⛩️'s 28 year old custom map he made and made a web-based Quake 2 with Fable on fast mode 🤓 You can now play it here: 👉 👈 It took a bit of hacking because the textures didn't load the first time, so I repacked some PAK files and now it works! AI is so good at reviving old stuff from your backups, I was always waiting for some backup app to come to finally be able to browse all my old files and figure stuff out from it, and now you can with AI

@levelsio

206,967 次观看 • 2 个月前

Sure you can make something like this with AI, but it's not as interesting if you think that Lynch wrote down this after doing Transcendental Meditation, showed it to some Sony exec, then showed it to some Production Designer, the whole team and then a bunch of people had to get together to build the scenes, make the props, make the sounds, light the scene and edit this whole thing. It hits different

Sure you can make something like this with AI, but it's not as interesting if you think that Lynch wrote down this after doing Transcendental Meditation, showed it to some Sony exec, then showed it to some Production Designer, the whole team and then a bunch of people had to get together to build the scenes, make the props, make the sounds, light the scene and edit this whole thing. It hits different

VIKARE

67,241 次观看 • 6 个月前

"At school or university, the thing is to be brilliant and to get the answer right first time. And there are brilliant people who can do that, but for the rest of us, we're not brilliant. And to get there, we have to strive and we have to go through failure. And we realize that you don't get it right first time, you don't get it right second time. In my case, and I counted it, it's 5,127 times. One of the things I always want to say is that sounds like a struggle. It was a struggle, but actually it was a hugely enjoyable struggle. The debt was mounting and I had three children, a wife and a home, and then a mortgage to pay, like everybody else. But I had a real point in life, I had a real aim and I had to get there. And the failures were interesting because I'd learned from every single one of them."

"At school or university, the thing is to be brilliant and to get the answer right first time. And there are brilliant people who can do that, but for the rest of us, we're not brilliant. And to get there, we have to strive and we have to go through failure. And we realize that you don't get it right first time, you don't get it right second time. In my case, and I counted it, it's 5,127 times. One of the things I always want to say is that sounds like a struggle. It was a struggle, but actually it was a hugely enjoyable struggle. The debt was mounting and I had three children, a wife and a home, and then a mortgage to pay, like everybody else. But I had a real point in life, I had a real aim and I had to get there. And the failures were interesting because I'd learned from every single one of them."

David Senra

137,546 次观看 • 8 个月前

I had my AI agent make me a TV show... and it went totally off the rails! Giving you the full scoop on how to use it in invideo right here 👇

I had my AI agent make me a TV show... and it went totally off the rails! Giving you the full scoop on how to use it in invideo right here 👇

TechHalla

76,257 次观看 • 3 个月前

With the latest fixes in ds4 I can now get it to build and iterate on a little TUI Tetris game just fine. Pretty damn cool (yes, it made some rendering errors)

With the latest fixes in ds4 I can now get it to build and iterate on a little TUI Tetris game just fine. Pretty damn cool (yes, it made some rendering errors)

Armin Ronacher ⇌

55,442 次观看 • 3 个月前

How Jason Calacanis Got Claw-Pilled: An AI Agent Prompted Itself to Build Him a CRM in Seconds “ The moment I became Claw-pilled, I was like, ‘Hey, I want to build my network, I know these 20 people in Japan, I had dinner with them during my recent trip, I want to know who they know, so check out LinkedIn and other things, and who they're associated with, and make me a mind map of it, and then the next trip I want to meet with the next circle of those connections.’” “It's like, ‘Okay, I got the results,’ and it said, ‘Where do you want me to put them?’” “I was like, ‘Well, where can you put them?’” “And it said, ‘I can put it in a Google sheet, I can put it in a Notion table, I can put it here, I could give you a PDF, I could give you a CSV file, or I could write you a CRM.’ And I was like, ‘Yeah, sure, make me a CRM system…’ and it made a CRM system.” “I think maybe 1/1000 people working with AI have had that experience. Maybe it's 1/10,000, where your agent says, ‘I'll make you bespoke software.’ The context is so good because the memory's getting better. When did that happen?” Perplexity CEO Aravind Srinivas: “I think it happened with Opus 4.5. That was the inflection point when models started being amazingly good at orchestration, and reasoning, and tool calls.” “The models started becoming very good at handling the context, so the context window no longer became a problem, and that made it suddenly so good at doing very long orchestration tasks.” —------------------------------------------ Our episode is sponsored by the New York Stock Exchange - a modern marketplace and exchange for building the future. It all happens at the NYSE 🏛 -

How Jason Calacanis Got Claw-Pilled: An AI Agent Prompted Itself to Build Him a CRM in Seconds “ The moment I became Claw-pilled, I was like, ‘Hey, I want to build my network, I know these 20 people in Japan, I had dinner with them during my recent trip, I want to know who they know, so check out LinkedIn and other things, and who they're associated with, and make me a mind map of it, and then the next trip I want to meet with the next circle of those connections.’” “It's like, ‘Okay, I got the results,’ and it said, ‘Where do you want me to put them?’” “I was like, ‘Well, where can you put them?’” “And it said, ‘I can put it in a Google sheet, I can put it in a Notion table, I can put it here, I could give you a PDF, I could give you a CSV file, or I could write you a CRM.’ And I was like, ‘Yeah, sure, make me a CRM system…’ and it made a CRM system.” “I think maybe 1/1000 people working with AI have had that experience. Maybe it's 1/10,000, where your agent says, ‘I'll make you bespoke software.’ The context is so good because the memory's getting better. When did that happen?” Perplexity CEO Aravind Srinivas: “I think it happened with Opus 4.5. That was the inflection point when models started being amazingly good at orchestration, and reasoning, and tool calls.” “The models started becoming very good at handling the context, so the context window no longer became a problem, and that made it suddenly so good at doing very long orchestration tasks.” —------------------------------------------ Our episode is sponsored by the New York Stock Exchange - a modern marketplace and exchange for building the future. It all happens at the NYSE 🏛 -

The All-In Podcast

170,961 次观看 • 5 个月前

reKILL is not just the game itself. I also built a set of tools to be able to create the game and iterate faster. And one of the biggest is MapEditor. And it made it possible to design such big map.

reKILL is not just the game itself. I also built a set of tools to be able to create the game and iterate faster. And one of the biggest is MapEditor. And it made it possible to design such big map.

TheoTheDev

10,983 次观看 • 7 个月前

Opus 5 replaced Opus 4.8 for me, it was generally stronger in everything... except it shares some of the weird language quirks of Fable, including a love of density and FableSpeak. I had it make a game where you build railroads in knock-off Middle Earth:

Opus 5 replaced Opus 4.8 for me, it was generally stronger in everything... except it shares some of the weird language quirks of Fable, including a love of density and FableSpeak. I had it make a game where you build railroads in knock-off Middle Earth:

Ethan Mollick

117,164 次观看 • 1 个月前

Opus 4.7 cs GPT 5.4 “make a flappy bird clone” I’ve been running this test for a few models now and this test was the hardest to objectively say who did better. Opus grabbed another version game assets compared to GPT 5.4, - GPT 5.4 however, grabbed the correct game assets. Opus 4.7 beat it on creativity where it grabbed assets (maybe unknowingly) that had a much more diverse set, including nighttime modes and different bird colors GPT 5.4 was able to get the pacing of the game the first shot, whereas Opus had the game running much too fast and then much too slow. But was able to place the metal perfectly in the game card at the end where GPT 5.4 struggled over 10 iterations. All in all both models had essentially made a near perfect game after three shots and are far ahead of the competition in terms of reasoning and effort.

Opus 4.7 cs GPT 5.4 “make a flappy bird clone” I’ve been running this test for a few models now and this test was the hardest to objectively say who did better. Opus grabbed another version game assets compared to GPT 5.4, - GPT 5.4 however, grabbed the correct game assets. Opus 4.7 beat it on creativity where it grabbed assets (maybe unknowingly) that had a much more diverse set, including nighttime modes and different bird colors GPT 5.4 was able to get the pacing of the game the first shot, whereas Opus had the game running much too fast and then much too slow. But was able to place the metal perfectly in the game card at the end where GPT 5.4 struggled over 10 iterations. All in all both models had essentially made a near perfect game after three shots and are far ahead of the competition in terms of reasoning and effort.

Chris

423,821 次观看 • 4 个月前

//LOADING THE DEMO... This game prototype was made in 15 minutes with AI. All it took was a single prompt and a free tool. And it already features monetization with $PLAI, ready to launch for thousands of players when polished. You can be a gamedev. You can ship the next hit. And it won't have to take years. Take your first step. Join the closed alpha now:

//LOADING THE DEMO... This game prototype was made in 15 minutes with AI. All it took was a single prompt and a free tool. And it already features monetization with $PLAI, ready to launch for thousands of players when polished. You can be a gamedev. You can ship the next hit. And it won't have to take years. Take your first step. Join the closed alpha now:

PlayMind

32,138 次观看 • 1 年前

🚨 Literally Build Anything Including Your Own YouTube In One Prompt It's amazing what a mixture of frontier models can achieve with powerful infrastructure like the Abacus AI SuperComputer We combine Opus, GPT 5.5 and GLM to create a extremely smart agent that you can use to vibe-code your entire start-up! Do it over the weekend!

🚨 Literally Build Anything Including Your Own YouTube In One Prompt It's amazing what a mixture of frontier models can achieve with powerful infrastructure like the Abacus AI SuperComputer We combine Opus, GPT 5.5 and GLM to create a extremely smart agent that you can use to vibe-code your entire start-up! Do it over the weekend!

Bindu Reddy

8,551,053 次观看 • 1 个月前