Re:Anthropic publishes the 'system prompts' that make Claude...
by usaar333 on Tuesday August 27, 2024 @01:54PM
(#41370592)
It lowers the probability. It's well known LLMs have imperfect reliability at following instructions -- part of the reason "agent" projects so far have not succeeded.
[ Parent
| on HN ]
There are no comments on this comment yet.