
creative behemoth. research data and evaluations @lumalabsai | prev @xai
San Francisco
Joined July 2008
- Tweets18.2K
- Following3.6K
- Followers6.6K
- Likes28.5K
patrickᶜ retweeted
your job as a software engineer in 2026 is to scroll twitter for useful things to send to your agent
you can now test Artifacts repos locally!
- create, fork & import repos with wrangler dev
- clone & push without impacting what's in production
- repo events (repo.forked) can trigger your workflows locally, so you can test them before you deploy
big shoutout to @leostera for shipping this!
patrickᶜ retweeted
Latent Blend is one of the coolest ways to get genuinely novel visuals from image models.
Replying to @edwardsanchez
Latent Blend! an image model dedicated to embedding interpolation
I'll share a dedicated thread on this soon, here's a peek: graycrawford.com/?open=laten…
It's live on app.lumalabs.ai, ask the agent about Latent Blend :) or rightclick some images directly to blend sweep/grid
patrickᶜ retweeted
Saw someone say, “The internet was once a library and they turned it into a store,” and if you’re young I don’t think you can imagine how different the web used to be.
patrickᶜ retweeted
for the past few weeks, I’ve been exploring painting with Fable 5.2 in code. one of the most common critiques I heard about Opus 5.5’s paintings was that it was only emulating real art. I thought that was fair, so i’ve been asking Fable 5.2 to develop personas—artists with some sort of a back story and a consistent style roughly identifiable in time
not knowing what to expect, i’ve watched this project evolve in directions i never predicted. I give comments or steers, and Claude updates or revises the engines that power the brushes and paint. where paintings come up i like or find intriguing, i ask it to go deeper. these are some favorites.
each of these is a python program, some one to two thousand lines of code, that places every stroke through a simulated paint engine with different bristles. most take a few thousand strokes, but i’ve pushed much higher with varying results. Claude does not use an image model, nor render or trace in advance
patrickᶜ retweeted
System of a Down: SCARY PART SCARY PART SCARY PART
Me: Ah!!
System of a Down: Funny part funny part funny part!
Me: Haha, yes
System of a Down: SCARY
Me: AH!!
System of a Down: funny!
Me: Haha
patrickᶜ retweeted
The ADHD urge to be excellent at solving other people's highly complex
problems whileletting my
car registration expire for 8 months while actively thinking about it every single day
patrickᶜ retweeted
Astra made robot control look like a job for frontier LLMs.
But small VLMs already know what to do. They just don't know how. Turns out, simulation is all you need.
Meet ZAP. No real robot data, no frontier teacher. Matches Astra on real tasks, 3× faster, 17× cheaper. 🧵
(1/11)
You don’t always need a 𝐟𝐫𝐨𝐧𝐭𝐢𝐞𝐫 𝐦𝐨𝐝𝐞𝐥 to control a robot.
With 𝐳𝐞𝐫𝐨 𝐫𝐞𝐚𝐥-𝐫𝐨𝐛𝐨𝐭 𝐭𝐫𝐚𝐢𝐧𝐢𝐧𝐠 𝐝𝐚𝐭𝐚, our Qwen-based ZAP matched GPT-6 Astra on 10 real-world tasks, with ~𝟑× 𝐟𝐚𝐬𝐭𝐞𝐫 𝐫𝐞𝐬𝐩𝐨𝐧𝐬𝐞𝐬 at 𝟏/𝟏𝟕 𝐭𝐡𝐞 𝐜𝐨𝐬𝐭.
Accepted to 𝐂𝐨𝐑𝐋 𝟐𝟎𝟐𝟔 𝐋𝐚𝐭𝐞-𝐁𝐫𝐞𝐚𝐤𝐢𝐧𝐠 𝐑𝐞𝐬𝐮𝐥𝐭𝐬!
zero-real.github.io/
It takes a village to raise a robot 🤖 We started this journey back in May, and it’s been amazing to see it come together. 🥺 Huge thanks to our incredible team for all the hard work, creativity, and collaboration along the way!











































