Designer / Creative Technologist @ Adobe (Generative AI + Video) Previously @ Instagram (Reels) & Microsoft (HoloLens) (opinions are my own!)

Joined August 2014
I recently found a pic on my phone of my newborn daughter holding my finger. It made me think - everyone loves to joke about how "AI can't do hands", but I didn't think that was true anymore. So I challenged myself to create an AI film using ONLY shots of hands.
2
8
1,559
I turned my MacBook lid into a pop-up book hinge! The lid's angle sensor drives the paper folds and the windows light up and a tram rolls in as I open it. FaceTime camera tracks my head and adds parallax, so the screen feels like a window into a magical paper pop-up world ✨
1
6
388
What if you could control variable fonts with your face? A real live typeface 😄
1
5
149
Image generation + old-school print math + procedural animation (built with Opus 5.5) to make a riso still life that rots, regrows, and peels apart into its ink layers 🍌🍎 🍐
1
99
Having far too much fun with our Adobe design team's icon set and Opus 5.5 to make animations (music and SFX done with @AdobeFirefly)
1
2
250
What if picking an aspect ratio was more fun?
1
4
110
Some fun with Gemini 4 Argon ✨🌈 This is my favorite era to be a designer - so quick to spin up visual explorations.
1
9
380
Hot dog? 🌭🌭🌭
we announced Jev 1.14 on 10.14 at 1:14pm PT 🔥 a new and improved model, along with experimental features for our dreamers: • images • a new box type • longer context surprise, Jev was already able to see you! 👁️ BUT our bar for production-grade intelligence is quite high, so builders beware, these are preview features. enter the ~*~ danger zone ~*~ at your own risk. 🚨
1
250
Hot dog? Built with Jev's new image input and bounding box output
3
127
Built a quick "I Spy" prototype with the latest Jev update and it works on the Game of Thrones coffee cup shot 🔍
we announced Jev 1.14 on 10.14 at 1:14pm PT 🔥 a new and improved model, along with experimental features for our dreamers: • images • a new box type • longer context surprise, Jev was already able to see you! 👁️ BUT our bar for production-grade intelligence is quite high, so builders beware, these are preview features. enter the ~*~ danger zone ~*~ at your own risk. 🚨
2
3
271
Now that Jev can take images and output bounding boxes, I made a little "I spy" style prototype. This is fun! Nice work @typesafeai
1
155
Update: it works on the Game of Thrones coffee cup shot 🔍
39
So fun! Now that Jev can take images and output bounding boxes, I made a little "I spy" style prototype. Great updates @typesafeai!
we announced Jev 1.14 on 10.14 at 1:14pm PT 🔥 a new and improved model, along with experimental features for our dreamers: • images • a new box type • longer context surprise, Jev was already able to see you! 👁️ BUT our bar for production-grade intelligence is quite high, so builders beware, these are preview features. enter the ~*~ danger zone ~*~ at your own risk. 🚨
2
1
258
Update: it works on the Game of Thrones coffee cup shot 🔍
40
It might not look like it at first glance but I actually think this is the wildest thing I've made with AI! Every pixel of this video (and all the animation) is pure math functions. No 3D models, no meshes, no textures, no render farm, no keyframes, no rigging. It's completely done with ~1,500 lines of shader code that Opus 5.5 wrote while I art-directed the scene in natural language. Music and SFX generated with @AdobeFirefly 🧵
5
2
1
24
1,377
Unlike the slot machine of diffusion models, this scene is completely parameterized and precisely editable. Change the colors, materials, wear and tear, acting, lighting, camera optics... basically anything you want! It's incredibly art-directable and fast/easy to change attributes. Also basically infinite resolution and VERY tiny size - the whole film is ~76 KB of text, smaller than one frame of itself as a JPEG. Anyway my mind is totally blown.
1
1
2
197
Unlike the slot machine of diffusion models, this scene is completely parameterized and precisely editable. Change the colors, materials, wear and tear, acting, lighting, camera optics - basically anything you want. It's incredibly art-directable and fast/easy to change attributes. Also basically infinite resolution and VERY tiny size - the whole film is ~76 KB of text, smaller than one frame of itself as a JPEG. Anyway, my mind is kinda blown.
21
Built a little bit of velcro for my computer to stick any files or text that I want quick access to. Made with Gemini 4 Argon + @AdobeFirefly sound effects model for some velcro sounds 😅
1
1
3
307
Used Gemini 4 Argon to build a personal Teams app for my meetings where I can "fog up" the lens of my webcam with my breath and draw on it 🌬️
38
29
7
803
40,483
Making weird biological (?) goop with Gemini 4 Argon, very addicting to squish these guys around and the shaders are pretty impressive
4
1
19
736