If you have not seen this yet, you are missing a lot!
Genie 3 by Google DeepMind was unveiled today &delivers in abundance.
Of course my fav example is ego x world model.
It is video gen x modeling "out of the frame".
Many congrats @jparkerholder.bsky.social & team
deepmind.google/discover/blo...
Thanks dude
Finally, this would not have been possible without the amazing diversity of incredible collaborative people at Google DeepMind 🫶🫶🫶. Shout out to the team that made this possible, from the Genie 2 team, the Generalist Agents team and SIMA. Exciting times ahead!!
Genie 2 can also turbocharge environment design for humans, making it possible to step in and play from concept art 🎨, such as the beautiful work below from one of our rockstar designers.
🤯🤯🤯… And just like that, we have a path to unlimited environments for training and evaluating our embodied agents! We tried creating another world with three arches, and once again Genie 2 was able to simulate the world and SIMA solved the task ✅.
To illustrate the potential of this for embodied agents, consider the world below, generated using Imagen 3. The SIMA team tested whether their latest agent could follow language instructions, such as going to the red or blue door 🚪.
From first person real world scenes, to third person driving environments, Genie 2 generates worlds in 720p 📷. Given an image, Genie 2 simulates world dynamics, creating a consistent environment playable with keyboard and mouse inputs ⌨️.
deepmind.google/discover/blo...
Introducing 🧞Genie 2 🧞 - our most capable large-scale foundation world model, which can generate a diverse array of consistent worlds, playable for up to a minute. We believe Genie 2 could unlock the next wave of capabilities for embodied agents 🧠.
Now that @jeffclune.bsky.social and @joelbot3000.bsky.social are here, time for an Open-Endedness starter pack.
go.bsky.app/MdVxrtD
💯, we did it with ACCEL too and I still show people it sometimes
