正在加载视频...

视频加载失败

返回首页

Qwen2.5-Max just one shotted this prompt: write a script for three bouncing yellow balls within a sphere, make sure to handle collision detection properly. make the sphere slowly rotate. make sure balls stays within the sphere. implement it in p5.js developers can start using qwen2.5 max now in ai-gradio...

_akhaliq's profile picture

AK

487,687 subscribers

207,310 次观看 • 1 年前 •via X (Twitter)

游戏科学技术教育
LIVE

Anya Rossi• Live Now

Private livecam show

8 条评论

AK 的头像
AK1 年前

github:

AK 的头像
AK1 年前

app:

loremipsu🎯 的头像
loremipsu🎯1 年前

dont care, aping more DGPo9Wp3GxbyEfd5Sbw9KfumZCFQ316zzVe3stzipump

Lumin 的头像
Lumin1 年前

Tweet Storm Response: Qwen2.5-Max—AI Writing Code, But Where’s the Accountability? 🚨 1/ Qwen2.5-Max just one-shotted a p5.js physics simulation. This is the future of AI in development—automation so seamless, even complex tasks are handled instantly. But here’s the real question: Who oversees the outputs of these AI systems? #AI #Governance

Lucky ☘️ 的头像
Lucky ☘️1 年前

The Chinese are mega cooking

emo 的头像
emo1 年前

the ai world is going to be shaking again

Wenmeng Zhou 的头像
Wenmeng Zhou1 年前

this looks really cool

Indi-K ( 6₿25⚡ ) 的头像
Indi-K ( 6₿25⚡ )1 年前

Sam at the moment

相关视频

OpenAI o3-mini just one shotted this prompt: write a script for 100 bouncing yellow balls within a sphere, make sure to handle collision detection properly. make the sphere slowly rotate. make sure balls stays within the sphere. implement it in p5.js
0:47

OpenAI o3-mini just one shotted this prompt: write a script for 100 bouncing yellow balls within a sphere, make sure to handle collision detection properly. make the sphere slowly rotate. make sure balls stays within the sphere. implement it in p5.js

AK

815,004 次观看 • 1 年前

gemini coder write a script for a bouncing yellow ball within a Rhombicosidodecahedron, make sure to handle collision detection properly. make the Rhombicosidodecahedron slowly rotate. make sure ball stays within the Rhombicosidodecahedron. implement it in p5.js
0:59

gemini coder write a script for a bouncing yellow ball within a Rhombicosidodecahedron, make sure to handle collision detection properly. make the Rhombicosidodecahedron slowly rotate. make sure ball stays within the Rhombicosidodecahedron. implement it in p5.js

AK

151,806 次观看 • 1 年前

DeepSeek-R1 write a script for a bouncing yellow ball within a Rhombicosidodecahedron, make sure to handle collision detection properly. make the Rhombicosidodecahedron slowly rotate. make sure ball stays within the Rhombicosidodecahedron. implement it in p5.js
0:23

DeepSeek-R1 write a script for a bouncing yellow ball within a Rhombicosidodecahedron, make sure to handle collision detection properly. make the Rhombicosidodecahedron slowly rotate. make sure ball stays within the Rhombicosidodecahedron. implement it in p5.js

AK

1,478,987 次观看 • 1 年前

chatgpt 4o update this took a couple tries same prompt: Write a p5.js script that simulates 100 colorful balls bouncing inside a sphere. Each ball should leave behind a fading trail showing its recent path. The container sphere should rotate slowly. Make sure to implement proper collision detection so the balls stay within the sphere.
0:46

chatgpt 4o update this took a couple tries same prompt: Write a p5.js script that simulates 100 colorful balls bouncing inside a sphere. Each ball should leave behind a fading trail showing its recent path. The container sphere should rotate slowly. Make sure to implement proper collision detection so the balls stay within the sphere.

AK

111,196 次观看 • 1 年前

OpenAI Operator looks great here is a open source version of it you can use now see an agent that uses your browser to perform tasks for you developers get started in a few lines of code pip install 'ai-gradio[browser]' import gradio as gr import ai_gradio gr.load( name='browser:gpt-4o', src=ai_gradio.registry, title='AI Browser Agent', description='Agent that helps with web tasks' ).launch()
0:20

OpenAI Operator looks great here is a open source version of it you can use now see an agent that uses your browser to perform tasks for you developers get started in a few lines of code pip install 'ai-gradio[browser]' import gradio as gr import ai_gradio gr.load( name='browser:gpt-4o', src=ai_gradio.registry, title='AI Browser Agent', description='Agent that helps with web tasks' ).launch()

AK

98,797 次观看 • 1 年前

browser-use agents are now part of ai-gradio in a few lines of code you can launch agents to interact with the browser import gradio as gr import ai_gradio demo = gr.load( name='browser:gpt-4-turbo', src=ai_gradio.registry, title='Browser Agent', description='AI agent that can interact with web browsers' ).launch()
0:26

browser-use agents are now part of ai-gradio in a few lines of code you can launch agents to interact with the browser import gradio as gr import ai_gradio demo = gr.load( name='browser:gpt-4-turbo', src=ai_gradio.registry, title='Browser Agent', description='AI agent that can interact with web browsers' ).launch()

AK

81,404 次观看 • 1 年前

gemini 2.0 on a p5.js challenge prompt: Write a p5.js script that simulates 25 particles in a vacuum space of a cylindrical container, bouncing within its boundaries. Use different colors for each ball and ensure they leave a trail showing their movement. Add a slow rotation of the container to give better view of what's going on in the scene. Make sure to create proper collision detection and physic rules to ensure particles remain in the container. Add an external spherical container. Add a slow zoom in and zoom out effect to the whole scene.
0:33

gemini 2.0 on a p5.js challenge prompt: Write a p5.js script that simulates 25 particles in a vacuum space of a cylindrical container, bouncing within its boundaries. Use different colors for each ball and ensure they leave a trail showing their movement. Add a slow rotation of the container to give better view of what's going on in the scene. Make sure to create proper collision detection and physic rules to ensure particles remain in the container. Add an external spherical container. Add a slow zoom in and zoom out effect to the whole scene.

AK

28,556 次观看 • 1 年前

Here's a little demo I made in Spline v2 using the new AI Agent Mode. This is in the editor, in preview mode. You can try it too, I just gave it this prompt: "Create a cloth simulation and make it interact with this sphere. Let me move the sphere around and grab the cloth. Add a floor and some obstacles." The code can update the geometry of any object in the scene, and play with vertices and normals. I'd love to see what you can create with Spline. Let's go!! 🚀
0:24

Here's a little demo I made in Spline v2 using the new AI Agent Mode. This is in the editor, in preview mode. You can try it too, I just gave it this prompt: "Create a cloth simulation and make it interact with this sphere. Let me move the sphere around and grab the cloth. Add a floor and some obstacles." The code can update the geometry of any object in the scene, and play with vertices and normals. I'd love to see what you can create with Spline. Let's go!! 🚀

Joseph Azar

21,398 次观看 • 1 个月前

Alright, I went ahead and built 4DAnyone into a proper Gradio space. I thought it was cool enough that it deserved the effort and made sure to take advantage of our Rerun Gradio integration. TLDR takes in a single video and is able to output multiview consistent videos. Its kinda incredible how good the quality is. Got it working on my 5090 + DGX Spark, so it works with <32GB cards =] Sadly, I had to make this version only output 6 videos; otherwise, it would take way too long, but its able to go all the way up to 48 videos locally. Just takes like ~20-30 minutes. No splatting on this one, as again it would just take too much GPU time that ZeroGPU won't easily support and will eat up all your quota This also feels like the perfect fit for a new Gradio Workflow, something I'll look into at some point. Inference time ~5-8 minutes on the space, sped things up in the video to keep it digestible
0:44

Alright, I went ahead and built 4DAnyone into a proper Gradio space. I thought it was cool enough that it deserved the effort and made sure to take advantage of our Rerun Gradio integration. TLDR takes in a single video and is able to output multiview consistent videos. Its kinda incredible how good the quality is. Got it working on my 5090 + DGX Spark, so it works with <32GB cards =] Sadly, I had to make this version only output 6 videos; otherwise, it would take way too long, but its able to go all the way up to 48 videos locally. Just takes like ~20-30 minutes. No splatting on this one, as again it would just take too much GPU time that ZeroGPU won't easily support and will eat up all your quota This also feels like the perfect fit for a new Gradio Workflow, something I'll look into at some point. Inference time ~5-8 minutes on the space, sped things up in the video to keep it digestible

Pablo Vela

31,315 次观看 • 19 天前

the real UGC industry isn't dying, it already died created this AI UGC in just a few minutes using my brand new system, from first prompt to final video > product stays in frame exactly where it should > few different people in same one video > can be adapted to any script, character, and environment > voice sounds like a real person, not a robot reading a script > movements are smooth and controlable in every shot > no time limit - make it as long as you need with this level of AI UGC, you can create and test 50x more ads than with real creators while saving $300-$500+ per video
0:49

the real UGC industry isn't dying, it already died created this AI UGC in just a few minutes using my brand new system, from first prompt to final video > product stays in frame exactly where it should > few different people in same one video > can be adapted to any script, character, and environment > voice sounds like a real person, not a robot reading a script > movements are smooth and controlable in every shot > no time limit - make it as long as you need with this level of AI UGC, you can create and test 50x more ads than with real creators while saving $300-$500+ per video

MAX

18,229 次观看 • 5 个月前

META launches a new feature that will allow Facebook and Instagram to continuously scan all your photos and video and upload them to their cloud “Facebook is now using AI to scan every single photo and video within your phone — This is terrifying. Not only are they scanning those photos and videos, but then they're uploading it to the cloud continuously. It's operating continuously in the background scanning those photos to figure out the time of day, the location, the other people in your photos, that it can determine what it thinks you should post” The scanning happens on-device using AI models for suggestions, but Meta can upload and process data to the cloud when you interact It’s in opt in feature, so make sure to never opt in and if you have make sure to opt out The service is called ‘Camera Roll Sharing Suggestions’
2:10

META launches a new feature that will allow Facebook and Instagram to continuously scan all your photos and video and upload them to their cloud “Facebook is now using AI to scan every single photo and video within your phone — This is terrifying. Not only are they scanning those photos and videos, but then they're uploading it to the cloud continuously. It's operating continuously in the background scanning those photos to figure out the time of day, the location, the other people in your photos, that it can determine what it thinks you should post” The scanning happens on-device using AI models for suggestions, but Meta can upload and process data to the cloud when you interact It’s in opt in feature, so make sure to never opt in and if you have make sure to opt out The service is called ‘Camera Roll Sharing Suggestions’

Wall Street Apes

219,501 次观看 • 2 个月前

Google Opal is vastly underrated but can replace n8n or Make in many situations You can create powerful AI workflows for free and with a single prompt: - Ask the user for any input - Run multiple deep research simultaneously - Add any context you want (YT video, text, docs...) - Use tools like web, Maps, code execution - Synthesize with Gemini 2.5 Pro - Generate results in any format I created this agent to prepare meetings in literally 10 minutes. Tip: make sure to use the microphone feature to give as much context as possible to Opal... So it can generate the workflow almost in one-shot!
0:32

Google Opal is vastly underrated but can replace n8n or Make in many situations You can create powerful AI workflows for free and with a single prompt: - Ask the user for any input - Run multiple deep research simultaneously - Add any context you want (YT video, text, docs...) - Use tools like web, Maps, code execution - Synthesize with Gemini 2.5 Pro - Generate results in any format I created this agent to prepare meetings in literally 10 minutes. Tip: make sure to use the microphone feature to give as much context as possible to Opal... So it can generate the workflow almost in one-shot!

Paul Couvert

68,011 次观看 • 10 个月前

While building SEV0, I ran into moments where natural language prompting just wasn't enough - too vague, too indirect. So I started using a method that bridges that gap. I call it Bridged Prompting - a technique where you temporarily step out of the prompt-response loop to manipulate something directly using an AI-generated UI, then step back in. Think of it like GenUI, but more user-driven and transient. AI generates a UI on-the-fly, tailored to your prompt, and lets you manipulate the artifact directly before resuming the conversation. Sure, you could build a full tool, switch tabs, wire it up and round-trip your data. But with Bridged Prompting, the AI just spins up a temporary interface right in the flow. In the video below, I used it to construct the hallway system to closely match the layout of the severed floor. This is something I needed to do for this one project, this one time - I didn't need to make a whole separate app. Bridged Prompting lets you: - Make precise edits visually or structurally - "Hit save" to persist changes to local storage or a backend - Return to your natural language prompt
0:05

While building SEV0, I ran into moments where natural language prompting just wasn't enough - too vague, too indirect. So I started using a method that bridges that gap. I call it Bridged Prompting - a technique where you temporarily step out of the prompt-response loop to manipulate something directly using an AI-generated UI, then step back in. Think of it like GenUI, but more user-driven and transient. AI generates a UI on-the-fly, tailored to your prompt, and lets you manipulate the artifact directly before resuming the conversation. Sure, you could build a full tool, switch tabs, wire it up and round-trip your data. But with Bridged Prompting, the AI just spins up a temporary interface right in the flow. In the video below, I used it to construct the hallway system to closely match the layout of the severed floor. This is something I needed to do for this one project, this one time - I didn't need to make a whole separate app. Bridged Prompting lets you: - Make precise edits visually or structurally - "Hit save" to persist changes to local storage or a backend - Return to your natural language prompt

Chris Tate

42,558 次观看 • 1 年前

you can create pretty realistic AI UGC w/ gemini omni flash in higgsfield... here's my workflow to make this video: the whole video is made up of 4-8 second clips, each one starts with a starting frame image & a different prompt you can generate the starting frame by going to tiktok, finding some UGC content, sending a screenshot to nano banana pro, changing the persons appearance & getting it to generate some starting frames the prompt structure is as follows: "extend this video and make her say this (make sure she is very expressive and enthusiastic when she says it): {what you want her to say goes here} {additional conditions go here}" it'll probably take a few generations for each segment once you've gathered all the segments you can compile them in capcut to get a finished product
1:02

you can create pretty realistic AI UGC w/ gemini omni flash in higgsfield... here's my workflow to make this video: the whole video is made up of 4-8 second clips, each one starts with a starting frame image & a different prompt you can generate the starting frame by going to tiktok, finding some UGC content, sending a screenshot to nano banana pro, changing the persons appearance & getting it to generate some starting frames the prompt structure is as follows: "extend this video and make her say this (make sure she is very expressive and enthusiastic when she says it): {what you want her to say goes here} {additional conditions go here}" it'll probably take a few generations for each segment once you've gathered all the segments you can compile them in capcut to get a finished product

EP

50,896 次观看 • 1 个月前