Meta wants to make it harder for hackers to trick AI
Briefly

"There's no real ground truth: We're still trying to find our way into how to evaluate these models" and need to "build a community to help standardize these things," says Joseph Spisak, Meta's director of product management for generative AI.
Purple Llama is a reference to what you get when red teams (attacking teams) and blue teams (defense) are combined and added to Meta's open-source foundational model.
Read at Axios
[
]
[
|
]