
Yejin Choi: teaching AI common sense and morality
The Robot Brains Podcast
00:00
The Challenges of Common Sensitivity in Pre-Training
It seems to open up very exciting research directions because it seems like a big open question. Then how do you reformulate the pre-training such that it's truly seeking, looking for correctness? I love the challenge of being able to abstract away this unspoken common sense knowledge about how the world works based on just raw internet data or YouTube videos.
Transcript
Play full episode