News for hackers. Stuff that matters.
Re:Genie 3: A new frontier for world models by yanis_t on Tuesday August 05, 2025 @10:20AM (#44798310)
And unfortunately not possible to play around for the general public.
Re:Genie 3: A new frontier for world models by hodgehog11 on Tuesday August 05, 2025 @10:27AM (#44798397)
This kind of announcement without an appropriate demo to verify their claims is pretty common with DeepMind at this point. They barely even discuss their limitations, so as always, this should be taken with a grain of salt.
Re:Genie 3: A new frontier for world models by Miraste on Tuesday August 05, 2025 @10:54AM (#44798804)
Most of the big labs never go into their models' limitations. OpenAI does it best, despite their inveterate hype-building. Their releases always have a reasonable limitations section, usually with text/image/video examples of failures.
Re:Genie 3: A new frontier for world models by horhay on Wednesday August 06, 2025 @05:34AM (#44809830)
Google does a good job with that too usually. Which makes their last two announcements (IMO success and Genie 3) being a bit light on details is somewhat surprising.
Re:Genie 3: A new frontier for world models by cj on Tuesday August 05, 2025 @10:22AM (#44798326)
> World models are also a key stepping stone on the path to AGI, since they make it possible to train AI agents in an unlimited curriculum of rich simulation environments.

I don't think Humans are the target market for this model, at least right now.

Sounds like the use case is creating worlds for AI agents to play in.

Re:Genie 3: A new frontier for world models by qingcharles on Tuesday August 05, 2025 @11:09AM (#44799014)
Here's a (weaker) competitor that's live:

https://odyssey.world/introducing-interactive-video

Re:Genie 3: A new frontier for world models by romanovcode on Tuesday August 05, 2025 @02:05PM (#44801863)
Yeah, honestly - what's the point of announcing it then?

I DECLARE BANKRUPTCY vibes here