Ryan DeLuca - @VR retweeted
SOTA next frame prediction model, now real time. Wild how fast this stuff moves. Also, sick video :)
Ryan DeLuca - @VR retweeted
Imagine explaining to your newly rejuvenated parents (who would otherwise have died of old age) that you once opposed the very technology that helped reverse their aging and wanted to slow it down because you didn’t like AI generated pictures.
Ryan DeLuca - @VR retweeted
I regret to inform you that the best gym program is repeating the same 10-12 exercises and getting stronger at them until you die.
Ryan DeLuca - @VR retweeted
FSD could literally free up OVER $1.5 trillion/yr... WHY isn't anyone talking about this??
If Lawmakers were serious about serving the people, they would start focusing on how to speed up FSD adoption.
The Data:
Fatal & serious crashes cost the U.S. almost $2 trillion per year in total societal harm; including ~$400 billion in direct economic costs in the form of:
- medical bills
- property damage
- lost wages
- enormous quality-of-life cost of lost years
- permanent disability
Tesla’s latest FSD data shows vehicles with FSD engaged are ~9× SAFER than the average driver.
That means, if fully adopted, FSD could produce savings the size of any one of these:
- ~6% of GDP
- The entire Social Security program
- Medicare AND Medicaid
- Roughly 2× the defense budget
At this scale, FSD (and technologies like it) could be one of the first real steps toward an age of AI "abundance" people talk about.
50 years from now, our children and grandchildren will look back in horror at the fact that we ever drove at all.
Ryan DeLuca - @VR retweeted
not enough people are mentally prepared for realtime persistent photorealistic 3D worlds built in nanoseconds around you
Ryan DeLuca - @VR retweeted
Lifting weights is one of the best things you can do for your cognitive and mental health.
Ryan DeLuca - @VR retweeted
Yann’s comment on the Roadster reminded me of another Stanford professor I interacted with years ago. Highly positioned and theoretically brilliant, they can’t turn numbers into coordinated atoms.
Their manufacturing knowledge came from The Economist. Factory visits involved VIP treatment with executives as workers buzzed around. They don’t grasp how atoms move in production or the ingenuity of turning equations into reality through choreographed coordination.
The most impressive manufacturing engineers I’ve worked with weren’t Ivy League graduates, yet they create things that catch your heart. They turn theoretical math into reality—the real magicians.
A month at Tesla taught me more than the most prestigious school could.
Ryan DeLuca - @VR retweeted
Fathers, pay attention to the way your children look for you.
Every time he makes a play, misses one, or steps up to the plate… he looks for me.
One day he won’t look for Daddy the same way.
So while you’re still the face they search for in the crowd, make sure they see love, pride, and reassurance looking back.
Every game doesn’t need a lecture. Sometimes your child just needs their dad.
Ryan DeLuca - @VR retweeted
liz warren: we’re gonna stop the mayonnaise company from buying a hot sauce company
elon musk:
Ryan DeLuca - @VR retweeted
Linus Torvalds says, rules prohibiting AI usage are “UTTERLY STUPID” and “idiotic”.
For the Linux kernel, Torvalds says, “we’re not going to make stupid rules that say ‘you can’t use tools for X’”.
Ryan DeLuca - @VR retweeted
webgpu for the win! The splats run so smoothly. A demo I built of a portal cube with some cool parallax (each scene was generated via world labs).
Ryan DeLuca - @VR retweeted
This "neural render" approach is the future of gaming and VR
🚀 Excited to introduce StreamRender-H3 — bringing real-time interactive worlds to life with diffusion models!
Built on Sol-Engine, we post-trained @MiniMax_AI H3 Ref2VA into a real-time streaming neural renderer.
🎮 Code drives the world. A game engine handles physics, object states, and player interactions, while H3 generates the visuals.
⚡ Real-time streaming: 2 denoising steps, 24 FPS, and ~273 ms per chunk on 8×GB200 GPUs.
🎨 One world, endless appearances: Change the reference image and prompt to render the same interactive world in entirely different styles.
🔥 Powered by streaming post-training, distillation, a fast causal H3 VAE, and full-stack inference acceleration.
Check out our demo and code! 👇
demo: nvlabs.github.io/Sana/Sol-En…
code: github.com/NVlabs/Sana/tree/…
Ryan DeLuca - @VR retweeted
Epic, by far one of the best technical leaders in games, is saying no hand written code. If you're not doing the same you will be left behind. It is over for non-AI workflows.




























