On deepmind
- Genie 3 remembers where you painted the wall
DeepMind's Genie 3 generates interactive worlds in real time at 720p that stay consistent for minutes. Persistence is the test for a world model, and it just got much better.
2 min reads likes comments - Genie 2 and World Labs in the same week
DeepMind's Genie 2 turns one image into a playable 3D world, and Fei-Fei Li's World Labs turns one image into a 3D scene you can walk through. Worlds are the next medium after text, images and video.
2 min reads likes comments - Search plus verification
AlphaProof and AlphaGeometry 2 together solved four of six problems from this year's Math Olympiad, reaching silver-medal level. What makes a checkable answer so useful for training, and what happens when there isn't one.
2 min reads likes comments - Genie learned to play from videos with no controls
DeepMind's Genie learned a controllable world model from 2D platformer videos with no action labels, by inferring eight latent actions on its own. The model learns the controls as well as the game.
2 min reads likes comments - One network, 604 tasks
DeepMind's Gato plays Atari, captions images, chats and stacks blocks with a real robot arm, all with the same weights. Turning actions into tokens is the interesting part.
2 min reads likes comments - We've been undertraining
DeepMind's Chinchilla paper says large language models have far too many parameters for the data they see. The fix is more data, and that raises a question about where it comes from.
2 min reads likes comments - One architecture, any input
DeepMind's Perceiver handles images, audio, video and point clouds with the same network, by cross-attending to a small latent array. Modalities stop needing their own models.
2 min reads likes comments - AlphaFold and learning physics from data
DeepMind's AlphaFold 2 predicts protein structures about as accurately as experiments do. A fifty-year-old physics problem, solved mostly by learning from examples.
2 min reads likes comments - MuZero learns the rules it isn't given
DeepMind's MuZero plays Go, chess, shogi and Atari at top level without being told the rules. It plans inside a model it learned, and the model only predicts what matters.
2 min reads likes comments - AlphaStar and the fairness of fast hands
DeepMind's StarCraft agent beat two pros 10-0, then lost the one game where it had to move a camera like a person. What counts as intelligence when the body is different.
2 min reads likes comments - AlphaGo Zero threw away human games and got better
Starting from random play, with no human data, it beat the version that beat Lee Sedol 100 games to 0 after three days. Human knowledge was a ceiling.
2 min reads likes comments - Ke Jie in Wuzhen
The world's top Go player lost 3-0 to AlphaGo in China this week, and Chinese viewers mostly couldn't watch it live. Why this match will matter more in China than the Lee Sedol one did.
2 min reads likes comments - 16,000 samples a second
DeepMind's WaveNet generates raw audio one sample at a time, and its speech sounds far more human than anything before. How, and why it's so slow.
2 min reads likes comments - Move 37
AlphaGo beat Lee Sedol four games to one. The move everyone is talking about, how the system found it, and why self-play is the part that matters.
2 min reads likes comments - 49 Atari games from pixels, and zero points in Montezuma's Revenge
DeepMind's DQN paper is in Nature. What the network actually learns, and the game where it learns nothing at all.
2 min reads likes comments