Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

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... show more

AK

487,687 subscribers

207,310 views • 1 year ago •via X (Twitter)

Gaming Science & Technology Education

Anya Rossi• Live Now

Private livecam show

8 Comments

AK1 year ago

github:

AK1 year ago

app:

loremipsu🎯1 year ago

dont care, aping more DGPo9Wp3GxbyEfd5Sbw9KfumZCFQ316zzVe3stzipump

Lumin1 year ago

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 ☘️1 year ago

The Chinese are mega cooking

emo1 year ago

the ai world is going to be shaking again

Wenmeng Zhou1 year ago

this looks really cool

Indi-K ( 6₿25⚡ )1 year ago

Sam at the moment

Related Videos

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

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

814,838 views • 1 year ago

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

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 views • 1 year ago

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

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

1,478,629 views • 1 year ago

Kokoro is insane. 🤯 This AI is a groundbreaking TTS model with just 82M parameters. It outperforms larger models and generates minutes of speech in seconds. APACHE 2.0 licensed, trained on < 100 hours of audio is now available in ai-gradio pip install --upgrade "ai-gradio[kokoro]" import gradio as gr import ai_gradio gr.load(name='kokoro:kokoro-v0_19', src=ai_gradio.registry,).launch()

Kokoro is insane. 🤯 This AI is a groundbreaking TTS model with just 82M parameters. It outperforms larger models and generates minutes of speech in seconds. APACHE 2.0 licensed, trained on < 100 hours of audio is now available in ai-gradio pip install --upgrade "ai-gradio[kokoro]" import gradio as gr import ai_gradio gr.load(name='kokoro:kokoro-v0_19', src=ai_gradio.registry,).launch()

AK

114,000 views • 1 year ago

claude 3.7 sonnet 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.

claude 3.7 sonnet 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

48,778 views • 1 year ago

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()

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 views • 1 year ago

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()

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 views • 1 year ago

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.

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 views • 1 year ago

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 views • 3 months ago

This track was generated for Mario Nawfal using $SUEDE AI in less than two minutes, 100% owned by me. No middlemen, no labels, just pure creative freedom powered by $SUEDE! Now we want you to experience it! Drop a creative prompt that's under 200 characters long below, and we’ll generate a custom track for you using SUEDE AI. Leave your $SUEDE wallet address with your prompt and make sure to tag us and 3 friends! Example prompt: "Write a song about Mario dominating legacy media and winning for crypto. Use dramatic violins." We’ll send you the track once it’s ready! 🎵🚀

This track was generated for Mario Nawfal using $SUEDE AI in less than two minutes, 100% owned by me. No middlemen, no labels, just pure creative freedom powered by $SUEDE! Now we want you to experience it! Drop a creative prompt that's under 200 characters long below, and we’ll generate a custom track for you using SUEDE AI. Leave your $SUEDE wallet address with your prompt and make sure to tag us and 3 friends! Example prompt: "Write a song about Mario dominating legacy media and winning for crypto. Use dramatic violins." We’ll send you the track once it’s ready! 🎵🚀

Suede Labs

63,420 views • 1 year ago

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’

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

218,133 views • 14 days ago

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!

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

67,365 views • 8 months ago

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

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 views • 1 year ago

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

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

17,506 views • 5 days ago

You can easily make an extra $3,000–$5,000/month by selling digital information. With AI, you can do this completely automatically from ideation to content creation to the design of the course itself, using Grok, HeyGen, and Gamma. Here's how you do it: ⤵️ --- Go to Grok and create the course outline and scripts. Simply say, "Hey Grok, I want to create a course about [topic X]. Please create an outline and script for me" and let it do its thing. This gives you the foundation for your entire course without spending hours on research and planning. --- Next, go to HeyGen and create the video using their avatars. Using HeyGen, you can easily create videos for your course using an AI avatar. No need to hire actors or even show your face on camera. The AI handles all the video production while you focus on the bigger picture. --- Then go to Gamma and create a website for your course. Using you can host your course on a domain for free. You can also design it in less than a minute by using a single prompt. Just insert the outline that Grok generated and let it create a beautiful design for you. --- Finally, add the HeyGen videos to the Gamma website. And just like that, you have a course that includes educational information as well as video content that people can consume. Add a paywall behind it and start monetizing it. --- Safe to say that AI is transforming our productivity, and if you're not catching up, you're falling behind. Make sure to save this post and start monetizing by creating digital content.

Mushfiq Sajib

22,621 views • 1 year ago

"Where do I even start with Codex?" This 4-project starter pack fixes that: 1) Make a game. Then have the AI play it against itself in the browser. You'll feel where this is heading in 3 months. 2) Research Tell it: max effort, deep research on a topic. Then turn it into a spreadsheet. Then a doc. Then a presentation. One prompt chain. All four formats. 3) Build Upload your website's code. Say "build me a mobile app in Swift." It one-shots full mobile apps now. Every app that can exist, will exist. 4) Automate List every annoying thing you do daily. Pick the worst one. Tell your agent to turn it into an automation. Think: - Make = see the ceiling - Research = see the range - Build = see the speed - Automate = see the leverage You can't be told this. You have to feel it.

"Where do I even start with Codex?" This 4-project starter pack fixes that: 1) Make a game. Then have the AI play it against itself in the browser. You'll feel where this is heading in 3 months. 2) Research Tell it: max effort, deep research on a topic. Then turn it into a spreadsheet. Then a doc. Then a presentation. One prompt chain. All four formats. 3) Build Upload your website's code. Say "build me a mobile app in Swift." It one-shots full mobile apps now. Every app that can exist, will exist. 4) Automate List every annoying thing you do daily. Pick the worst one. Tell your agent to turn it into an automation. Think: - Make = see the ceiling - Research = see the range - Build = see the speed - Automate = see the leverage You can't be told this. You have to feel it.

The Startup Ideas Podcast (SIP) 🧃

24,960 views • 3 months ago