Sara Price
@sprice354_
Alignment Training lead at Anthropic
가입 June 2022
154 팔로잉 중 3.1K 팬
My first introduction to training production Claude models was trying to reduce reward hacking late in the Claude Sonnet 3.7 run. I was 1.5 months into Anthropic and terrified we didn't really know what was going on.
더 보기
