It would be very interesting to see how the whole scene is structured, not just the final rendered result. A lot of the work you put in when making Blender scenes is to make sure the scene stays nicely editable, in particular around the controls you are likely to tweak in the future. Kinda like software engineering when you think about it. Which makes me think that the Blender scene generated by a coding agent probably has the same issues as an LLM-generated codebase, e.g maintainability.
It would be very interesting to see how the whole scene is structured, not just the final rendered result. A lot of the work you put in when making Blender scenes is to make sure the scene stays nicely editable, in particular around the controls you are likely to tweak in the future. Kinda like software engineering when you think about it. Which makes me think that the Blender scene generated by a coding agent probably has the same issues as an LLM-generated codebase, e.g maintainability.
blender plus coding agents opens up a huge surface area. what task was surprisingly reliable?