logoalt Hacker News

awongh12/09/20242 repliesview on HN

Interesting to see how bad the physics/object permanence is. I wonder if combining this with a Genie 2 type model (Google's new "world model") would be the next step in refining it's capabilities.


Replies

torginus12/09/2024

This feels like computer graphics and the 'screen space' techniques that got introduced in the Xbox 360 generation - reflection, shadows etc. all suffered from the inability to work with off screen information and gave wildly bad answers once off screen info was required.

The solution was simple - just maintain the information in world space, and sample for that. But simple does not mean cheap, and it led to a ton of redundant (as in invisible in the final image) having to be kept track of.

kranke15512/09/2024

Until these models can figure out physics, it seems to me they will be an interesting toy

show 2 replies