Edge 384: Inside Genie: Google DeepMind's Astonishing Model that can Build 2D Games from Text and Images
Was this email forwarded to you? Sign up here Edge 384: Inside Genie: Google DeepMind's Astonishing Model that can Build 2D Games from Text and ImagesThe model represents a new category in generative AI.The pace of research in generative AI is nothing short of remarkable. Even so, from time to time, there are papers that literally challenge our imagination about how far the generative AI space can go. A few weelks ago, Google DeepMind published some of that work with the release of Genie, a model that is able to generative interactive game environments from text and images. If we think video generation with models like Sora areimpressive, imagine inferring interacting actions in those videos. Imagine a scenario where the vast array of videos available on the Internet could serve as a training ground for models to not only create new images and videos but also to forge entire interactive environments. This is the vision that Google DeepMind has turned into reality with Genie, a groundbreaking approach to generative AI. Genie can craft interactive environments from a mere text or image prompt, thanks to its training on over 200,000 hours of publicly available gaming videos from the Internet. What makes Genie stand out is its ability to be controlled on a frame-by-frame basis through a learned latent action space, even though it was trained without specific action or text annotations. Genie’s Architecture...Subscribe to TheSequence to read the rest.Become a paying subscriber of TheSequence to get access to this post and other subscriber-only content. A subscription gets you:
|
Older messages
Edge 383: The Key Capabilities of Autonomous Agens
Tuesday, April 2, 2024
Planning, memory, profiling, action execution, knowledge management and several others. ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
Four New Major Open Source Foundation Models in a Week
Sunday, March 31, 2024
DBRX, Grok 1.5, Samba-CoE and Jamba are all bringing unique innovations to open source generative AI. ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
Edge 381: Google DeepMind's PrompBreeder Self-Improves Prompts
Thursday, March 28, 2024
The method combines chain of thoughts, plan and solve and evolutionary algorithms in a single mthod. ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
Edge 380: A New Series About Autonomous Agents
Tuesday, March 26, 2024
The series will cover memory, action execution, planning, collaboration and many other characteristics of autonomous agents. ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
📝 Guest Post: Zilliz Unveiled Milvus 2.4 at GTC 24, Transforming Vector Databases with GPU Acceleration*
Monday, March 25, 2024
Collaboration with NVIDIA boosts Milvus performance 50x ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
You Might Also Like
DeveloPassion's Newsletter #165 - She Said Yes ❤️
Saturday, May 4, 2024
Edition 165 of my newsletter, discussing Knowledge Management, Knowledge Work, Zen Productivity, Personal Organization, and more! Sébastien Dubois DeveloPassion's Newsletter DeveloPassion's
📧 Implementing API Gateway Authentication With YARP
Saturday, May 4, 2024
Implementing API Gateway Authentication With YARP Read on: my website / Read time: 5 minutes BROUGHT TO YOU BY Supercharging Development With AI and APIs Announcing Postman v11: Streamline API
Software Testing Weekly - Issue 218
Friday, May 3, 2024
Unit, Integration and End-to-End Tests 🔧 View on the Web Archives ISSUE 218 May 4th 2024 COMMENT Welcome to the 218th issue! I loved going through this discussion among software engineers: What is your
gpt2-chatbot and OpenAI search engine - Weekly News Roundup - Issue #465
Friday, May 3, 2024
Plus: Med-Gemini; Vidu - Chinese answer to OpenAI's Sora; the first race of Abu Dhabi Autonomous Racing League; deepfaking celebrities to teach math and physics; and more! ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
NASA comes to the rescue of crowded rocket launch sites
Friday, May 3, 2024
Plus: Fisker's legal woes and Sprinklr lays off 100 View this email online in your browser By Christine Hall Friday, May 3, 2024 Good afternoon, and welcome to TechCrunch PM. We made it to Friday,
🎮 Forget the PS5 Pro, I Still Love My PS4 — The Best Lock Screen Widgets for iPhone
Friday, May 3, 2024
Also: Smart Home Mistakes to Avoid, and More! How-To Geek Logo May 3, 2024 Did You Know Half of the world's geysers are located in Yellowstone National Park. 🔑 More Passkeys Happy Friday! You can
JSK Daily for May 3, 2024
Friday, May 3, 2024
JSK Daily for May 3, 2024 View this email in your browser A community curated daily e-mail of JavaScript news The Power of React's Virtual DOM: A Comprehensive Explanation Modern JavaScript
Musk raises $6B for AI startup
Friday, May 3, 2024
Also, is TikTok dodging Apple's commissions? View this email online in your browser By Haje Jan Kamps Friday, May 3, 2024 Welcome to Startups Weekly — Haje's weekly recap of everything you can
SWLW #597: Seek first to understand, The "Iterative Adjacent Possible", and more.
Friday, May 3, 2024
Weekly articles & videos about people, culture and leadership: everything you need to design the org that makes the product. A weekly newsletter by Oren Ellenbogen with the best content I found
iOS Dev Weekly - Issue 659
Friday, May 3, 2024
Is Swift 6 hitting one of the REAL hard problems? Not generics, not data race safety, but naming things! 😬 View on the Web Archives ISSUE 659 May 3rd 2024 Comment Naming things is one of the two hard