Will Whitney (@wfwhitney) header
Will Whitney (@wfwhitney) profile picture

Research Scientist at DeepMind. Former grad student at NYU, MIT undergrad, and YC founder.

San Francisco, CA
Joined April 2007
It was pretty funny following the chat thread as George worked on this over a weekend. "i said good job do 2x 6 hours ago and still hasnt stopped" "Lets goooo 🔥" and the numbers just kept getting better
Is it possible to make 3D Gaussian Splatting even faster? Short answer YES! Enjoy a 10.5x optimization on forward/backward cuda kernels over the published 3DGS ones! grgkopanas.github.io/3dgs_cu…
1
3
651
Argon++ are crazy good at this kind of work
57
Will Whitney retweeted
Had early access to Genie 4 from @GoogleDeepMind. This is a fully generated, interactive world from a single starting prompt (environment + character) 🤯 Feels like a massive step forward - you can now prompt to change the world and interact with it. With native audio!
152
188
74
2,370
209,058
Genie 4 is out! If Genie 3 felt like a simulation of a video game, Genie 4 feels like an interactive movie. The visuals are much more realistic, audio makes it feel immersive, and you can prompt for whatever you want during the experience.
This is Genie 4, our most realistic and interactive world model yet. 🌐 Explore dynamic environments in real time to see how the scene responds, sounds, and how the people in it move, react, and speak.
3
1
18
716
Will Whitney retweeted
Hi all, I have a new result I'm excited to share. It turns out that *all existing implementations* of softmax and cross-entropy (that's JAX, PyTorch, textbooks, etc) have a subtle bug --- two bugs, actually. A simple rewrite fixes both, and eliminates "slingshots" when grokking:
135
795
153
6,574
854,339
Will Whitney retweeted
Argon has this amazing natural understanding of the world. It can do so many things from first principles. Here's a pelican riding a bike, using fourier epicycles. Video made by Argon. Time-synced Lyria 3.5 music prompted by Argon.
235
591
240
8,419
2,248,216
Will Whitney retweeted
Kudos to Pope Leo. I am disturbed by how some of my fellow AI researchers keep trying to elevate the moral standing of checkpoints and harnesses. I hope the rest of us on Team Meatbag reject this movement and stay focused on solving real problems and helping actual humans.
NEW: According to a bombshell report in the New York Times, Anthropic co-founder Chris Olah threatened to walk out of Pope Leo XIV’s AI encyclical launch in May because the pope rejected the idea that machines can be conscious. Olah’s team then privately lobbied the pope’s advisers “to take the possibility of model consciousness seriously.” Pope Leo XIV held firm. For months, Anthropic has wined and dined theologians and religious scholars under nondisclosure agreements, hoping they would bless the idea that Claude has moral standing. thelettersfromleo.com/p/nyt-…
85
292
39
3,270
247,743
Introducing Gemini 4 Argon – our new frontier model. It’s built for complex workflows across coding, enterprise knowledge work, and cybersecurity defense – rolling out today to a set of trusted testers through our Fairwind Program.
1,979
4,610
4,525
42,705
9,056,859
Huge congratulations to the Project Genie team on taking home the Cannes Lions Grand Prix for AI Craft! 🎉 Thank you @Cannes_Lions for recognizing how Genie pushes beyond conventional creative limitations to achieve outcomes unattainable without frontier AI… Another unexpected consequence of scaling world models :) Try it yourself here: labs.google/projectgenie
21
60
10
322
114,566
omni bringing this concept to life as an ipad app
hey chatgpt, what's the weather like today?
1
1
6
2,737
Will Whitney retweeted
hey chatgpt, what's the weather like today?
🤖 Made with AI
5
2
1
52
8,332
Will Whitney retweeted
Over at Substack, @JoshEakle asks: "It's 2026, and I have yet to see an anti-almond farm protest."
117
558
84
5,791
935,397
Will Whitney retweeted
Real-world models are here! Stoked to share how we're bringing real-world locations to life by integrating Street View into Genie. Try it now at labs.google/fx/projectgenie and read the blog for more info: blog.google/innovation-and-a…
19
94
24
625
230,943
So sick! Better world models are going to unlock so many use cases like this
Genie 3 🤝 @Waymo The Waymo World Model generates photorealistic, interactive environments to train autonomous vehicles. This helps the cars navigate rare, unpredictable events before encountering them in reality. 🧵
2
8
752
Will Whitney retweeted
Environment: “34th Street–Penn Station” Character: “Discarded pack of cigarettes” Genie 3:
170
469
182
11,287
1,079,879
Very excited for people to be able to play with Genie! Seeing something you worked on in the wild is so different from playing with it by yourself
Step inside Project Genie: our experimental research prototype that lets you create, edit, and explore virtual worlds. 🌎
4
350
Will Whitney retweeted
I got early access to Project Genie from @GoogleDeepMind ✨ It's unlike any realtime world model I've tried - you generate a scene from text or a photo, and then design the character who gets to explore it. I tested dozens of prompts. Here are the standout features 👇
77
163
51
1,771
230,215
Come work with Joe and you’ll sit by me, @poolio, @jon_barron, @RuiqiGao, @holynski_, @tkipf, and many other fine folks!
We’re hiring student researchers at Google DeepMind for 2026. Come work with our great team in SF on anything from diffusion / world models / 3D. Send me an email if you’re interested!
2
3
30
8,341
Will Whitney retweeted
GEN-0 models exhibit strong scaling laws, in which more pretraining data and compute consistently (and predictably) improve downstream post-training performance of the model across many tasks. 🔬📈🧠
2
12
8
104
67,023
Every smart home product except lights would be better as a manual product operated by a robot
1
199