hapticdata's profile picture. Code @Google Creative Lab making AI accessible to everyone. Generative artist finding joy in programs making unexpected pretty pictures

Kyle Phillips

@hapticdata

Code @Google Creative Lab making AI accessible to everyone. Generative artist finding joy in programs making unexpected pretty pictures

置顶

Working on some mesh subdivision + displacement w/ toxiclibsjs and #threejs then OBJ into #cinema4d #generative

hapticdata's tweet image. Working on some mesh subdivision + displacement w/ toxiclibsjs and #threejs then OBJ into #cinema4d #generative
hapticdata's tweet image. Working on some mesh subdivision + displacement w/ toxiclibsjs and #threejs then OBJ into #cinema4d #generative
hapticdata's tweet image. Working on some mesh subdivision + displacement w/ toxiclibsjs and #threejs then OBJ into #cinema4d #generative

Kyle Phillips 已转帖

GemBooth! test out prompts in Gemini 2.5 Flash Image (aka 🍌 nano-banana 🍌) with your webcam


Kyle Phillips 已转帖

Infinite Wiki ⁕ Every word is a hyperlink. Every description is generated in real-time (in ~1 second) ⁕ Runs on Gemini 2.5 Flash Lite. ASCII diagrams using 2.5 Flash


Kyle Phillips 已转帖

We are proud to announce you can now build your own AI-powered apps on top of our GenAI SDK, in AI Studio, with just a simple prompt. Leverage the power of the Gemini API to create apps in less than a few minutes!


Kyle Phillips 已转帖

I had a lot of fun compiling the 30 Gemini demos in this video! If you want to play around, here are links to all of them in thread 🧵


Aaron's video toys is such a cool example of what you can do with just a youtube URL and such a fun way to learn anything! code is right there too. Highly recommend checking this one out.

Built this fun experiment called Video Toys that marries Gemini long-context video understanding with Gemini 2.5 code generation to help with learning 💡 Give it a YouTube video and it decides what kind of app would be helpful—and then builds it. The idea is that whatever app it…



Really love PDF -> Interactive Toy with Gemini Canvas 📄🪀. I tried giving it white papers on various algorithms related to generative art. This one is for the white paper "evenly-spaced streamlines" Try it: gemini.google.com/corp/share/cef…

Though this ☝️ more toy than tool I think it's pointing at a cool learning future where we fluidly convert between mediums: Docs to Podcasts PDFs to Apps ..Whatever works for you Reminds me of when we invented a song to teach my young kid our phone numbers. He still sings it



Kyle Phillips 已转帖

Prompt Commander I asked Gemini 2.5 Pro to create a little retro trainer game based on 69-page tutorial by Google on Prompt Engineering. I loaded up the PDF and a few prompts later got this silly little game 😃 I left the few bugs in as its cool to see what Gemini came up…

Google literally published a 69-page prompt engineering masterclass

aaditsh's tweet image. Google literally published a 69-page prompt engineering masterclass
aaditsh's tweet image. Google literally published a 69-page prompt engineering masterclass


Kyle Phillips 已转帖

What it would be like to co-think creatively with AI? After you draw, Gemini gives suggestions on what it can add to the drawing, picks one, and automatically adds it. Built on Gemini Co-Drawing by @trudypainter and @alexanderchen!

Co-draw with Gemini 2.0 native image generation… from @alexanderchen and me Doodling + AI is a magical → it really starts to feel like Gemini is *with you in the canvas Link: huggingface.co/spaces/Trudy/g…



Kyle Phillips 已转帖

Now we can create 3D scenes with Gemini and Three.js! 💥 g.co/gemini/share/2…


Kyle Phillips 已转帖

It's been awesome collaborating with @GoogleDeepMind robotics team! It is amazing to see the low latency of action prediction now. We used Gemini 2.0 live API to enable voice interaction (built w/ @hapticdata) which you can see in the video below. 👇▶️

Gemini Robotics is out and is the most advanced VLA in the world! I am especially blown away by the instruction following results: it is the first time where I personally have felt that building generic embodied intelligence is within reach! Like a robot coming to life.



It was really incredible getting the chance to work on this, these teams are so great! Using my voice to instruct these robots and explore spatial reasoning was a real glimpse into the future of physical AI

Gemini Robotics is out and is the most advanced VLA in the world! I am especially blown away by the instruction following results: it is the first time where I personally have felt that building generic embodied intelligence is within reach! Like a robot coming to life.



Loading...

Something went wrong.


Something went wrong.