←back to thread

Interview with gwern

(www.dwarkeshpatel.com)
308 points synthmeat | 2 comments | 14 Nov 24 08:56 UTC | HN request time: 0.211s | source
Show context
dewey ◴[14 Nov 24 11:38 UTC] No.42135232[source]▶
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.
replies(2): >>42135259 #>>42136103 #
djmips ◴[14 Nov 24 11:42 UTC] No.42135259[source]▶
How about just listening to the interview then?
replies(1): >>42135351 #
1. dewey ◴[14 Nov 24 11:56 UTC] No.42135351[source]▶
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.

I know it's probably a "me problem" ;)

replies(2): >>42135980 #>>42141813 #
2. luke-stanley ◴[14 Nov 24 13:30 UTC] No.42135980[source]▶
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.