Загрузка видео...
Не удалось загрузить видео
Google DeepMind just dropped 'Genie', an AI that can generate interactive video games. This is a huge deal. Genie is trained on 200,000 hours of unsupervised public internet gaming videos and can generate video games from a single prompt or image. But here's what's insane: Despite not being trained... show more
3,376,834 просмотров • 2 лет назад •via X (Twitter)
Комментарии: 11

Google DeepMind also trained Genie on robotics videos as a proof-of-concept for potential world model applications in robotics. The team lead for Genie: "We think this is a promising step towards general world models for AGI."

If you want to learn more, I'll be going more in-depth on Genie in my newsletter tomorrow. I'll also dive into Mistral Large, Google Pixel's Gemini upgrades, open-source text-to-video, and more. Subscribe, and you'll never miss a thing in AI ever again:

Waiting in the next 2 hours for OpenAI to drop ChatGPT 4.5 or something else world-changing. And steal the lights from Google :) Again.

Would definitely make sense for them to drop something right about now

From text-to-movies to now text-to-games…what a future ahead 🤯

Not gonna lie, I didn’t think we’d see an actual interactive AI video game in 2024. But here we are, in February

Absolute garbage

but can it generate crysis

I am a gaming browser for everyone except people that play this

All of the examples look like the same 1980s-style game with slightly different designs. It’ll be exciting to see this evolve, though.

It’s like the first version of Midjourney. Just the beginning.

