Interesting idea with the avatar, but I feel like just having a voice and some audio waves would be better than trying to create a talking avatar. Could just be my personal preference of not having a mental image of someone unknown I guess? Similar to reading a book after watching the movie adaptation.
In my country, when TV series are interviewing anonymous people they use specific visual language - pixellated face, or facing away from the camera, or face clad in shadow.
Having an actor voice the words is normal. But having an actor showing the anonymous person's face is an... unusual choice.
I'm aware of that possibility but I don't mind watching the other interviewer and I'm also not sure if there's something being shown (screenshots etc.) after the first few minutes I watched.
It does make me wonder what easy way to do ML assisted shot / person detection and `blanking` is. I'm just gonna point out there is a nerd snipe danger here ;D
Although the avatar tool is probably not SOTA, I thought the 3D model was a really cool way to deal with interviewing Gwern, I am quite enjoying the current video.
