The document discusses a new AI assistant created by Anthropic to be helpful, harmless, and honest. The assistant is designed according to Constitutional AI techniques to ensure its behavior and answers respect human preferences and don't cause unintended harm. It is being developed through a method of progressive alignment to guarantee it remains beneficial as it becomes more capable.
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0 ratings0% found this document useful (0 votes)
33 views40 pages
BPC 7.0
The document discusses a new AI assistant created by Anthropic to be helpful, harmless, and honest. The assistant is designed according to Constitutional AI techniques to ensure its behavior and answers respect human preferences and don't cause unintended harm. It is being developed through a method of progressive alignment to guarantee it remains beneficial as it becomes more capable.