Sara Price
@sprice354_
Alignment Training lead at Anthropic
加入 June 2022
154 正在關注 3.1K 粉絲
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.
顯示更多
