News for hackers. Stuff that matters.
Re:Anthropic publishes the 'system prompts' that make Claude... by nitwit005 on Tuesday August 27, 2024 @01:29PM (#41370280)
It's possible it reduces the rate but doesn't fix it.

This did make me wonder how much of their training data is support emails and chat, where they have those phrases as part of standard responses.

There are no comments on this comment yet.