@sriyash.bsky.social
Reposted
Q&A: New AI training method lets systems better adjust to users’ values www.washington.edu/news/2024/12...
Q&A: New AI training method lets systems better adjust to users’ values
University of Washington researchers created a method for training AI systems — both for large language models like ChatGPT and for robots — that can better reflect users’ diverse values. It...
www.washington.edu
December 18, 2024 at 6:41 PM
Q&A: New AI training method lets systems better adjust to users’ values www.washington.edu/news/2024/12...
Reposted
UW News put out a Q&A about our recent work on Variational Preference Learning, a technique for personalizing Reinforcement Learning from Human Feedback (RLHF) washington.edu/news/2024/12...
Q&A: New AI training method lets systems better adjust to users’ values
University of Washington researchers created a method for training AI systems — both for large language models like ChatGPT and for robots — that can better reflect users’ diverse values. It...
washington.edu
December 18, 2024 at 9:51 PM
UW News put out a Q&A about our recent work on Variational Preference Learning, a technique for personalizing Reinforcement Learning from Human Feedback (RLHF) washington.edu/news/2024/12...