Stanford CS25: V4 I Aligning Open Language Models

Transcript

Today we're happy to have Nathan Lambert, a research scientist at the Allen Institute for AI, who focuses on RLHF and the author of interconnects.ai. He'll be presenting a really cool talk on aligning open language models today. So thank you for joining us, Nathan. Yeah, thanks for the intro. OK, this is a long time coming. This is a brief intro on... Read More