26 karma · joined September 8, 2021
For Remotion, the AI determines what resources the scene will need, whether that be images, generated assets, or prebuilt visual components. This part doesn't happen in Manim because its more for math based visualizations.
Re costs, both workflows have a series of presets that make the implementation less expensive and more consistent. The reduction in price for the Terra model series has been particularly helpful for us.
1) The initial prompt where you type what you want to learn
2) There are a couple universal follow up questions that ask the depth and breadth you want to learn at
3) There are then some course specific intent questions we ask that ask content specific questions. For example if you type "History of NYC" we might ask "What time period do you want to focus on?"