Scale: The Data Platform for AI; High quality training and validation data for AI applications
Artificial Artificial Artificial Intelligence: Crowd Workers Widely Use Large Language Models for Text Production Tasks
Sparrow: Improving alignment of dialogue agents via targeted human judgements
https://openai.com/blog/chatgpt/
Deep reinforcement learning from human preferences
https://arxiv.org/pdf/2209.14375#page=25&org=deepmind
Geoffrey Irving
https://www.lesswrong.com/tag/debate-ai-safety-technique-1
John Schulman’s Homepage
https://www.youtube.com/watch?v=hhiLw5Q_UFg&t=1098s