Uhhh, yes. It's in the devblogs. They call it prompt adherence hierarchy or something, where system instructions (oAI) > dev instructions (you) > user requests. They've been training this way specifically, and test for it in their "safety" analysis. Same for their -oss versions, so tinkerers might look there for a tinker friendly environment where they could probably observe the same kinds of behaviour.
Uhhh, yes. It's in the devblogs. They call it prompt adherence hierarchy or something, where system instructions (oAI) > dev instructions (you) > user requests. They've been training this way specifically, and test for it in their "safety" analysis. Same for their -oss versions, so tinkerers might look there for a tinker friendly environment where they could probably observe the same kinds of behaviour.
1 - https://cdn.openai.com/pdf/8124a3ce-ab78-4f06-96eb-49ea29ffb...