|
|
|
|
|
|
by scotty79
636 days ago
|
|
|
This is wonderful. "As part of developing these new models, we have come up with a new safety training approach that harnesses their reasoning capabilities to make them adhere to safety and alignment guidelines. By being able to reason about our safety rules in context, it can apply them more effectively." "We made the AI slightly less likely to go rogue and kill us all. You're welcome." |
|
|