News for hackers. Stuff that matters.
Re:Anthropic publishes the 'system prompts' that make Claude... by ttul on Tuesday August 27, 2024 @12:21PM (#41369246)
I believe that the system prompt offers a way to fix up alignment issues that could not be resolved during training. The model could train forever, but at some point, they have to release it.

There are no comments on this comment yet.