I am trying to improve my approach to AI Model Security and could use some practical advice.
I am particularly interested in evaluation and prompt design. I would like to compare approaches that people have actually used rather than just theoretical suggestions.
What would you tell someone trying this for the first time?
I am particularly interested in evaluation and prompt design. I would like to compare approaches that people have actually used rather than just theoretical suggestions.
What would you tell someone trying this for the first time?