6 points | by namanbhargava18 5 hours ago ago
4 comments
I’m a bit skeptical about LLMs actually being able to perceive 3D context properly. I think a well-designed structured scene graph could be promising.
I have tried a lot of AI 3D stuff but nothing is usable in actual games. Sometimes it makes my character rigs so weird that I am unable to animate it.
true, what we have seen, agent can place the rigg decently well but where it's performs bad is assigning the weight paints. we're working to solve this. more updates soon!
I’m so bullish on the idea that LLMs will solve spatial understanding themselves. World model makers can succ ma d.
I’m a bit skeptical about LLMs actually being able to perceive 3D context properly. I think a well-designed structured scene graph could be promising.
I have tried a lot of AI 3D stuff but nothing is usable in actual games. Sometimes it makes my character rigs so weird that I am unable to animate it.
true, what we have seen, agent can place the rigg decently well but where it's performs bad is assigning the weight paints. we're working to solve this. more updates soon!
I’m so bullish on the idea that LLMs will solve spatial understanding themselves. World model makers can succ ma d.