alt Hacker NewsWould they not have RL'd Claude such that we picked the one most likely to not complain and emit those stop tokens? Otherwise they wouldn't be useful. Seems flawed...
Would they not have RL'd Claude such that we picked the one most likely to not complain and emit those stop tokens? Otherwise they wouldn't be useful. Seems flawed...
It's really an end_conversation tool call. We don't know for sure, but training in a way that puts optimization pressure on its usage (in either direction) feels like it would defeat the purpose.