alt Hacker NewsThere are two different things:
- was item X in the training data
- did the inclusion of X in the training data lead to Y
I understand why the second is hard, but why is the first one hard?
There are two different things:
- was item X in the training data
- did the inclusion of X in the training data lead to Y
I understand why the second is hard, but why is the first one hard?
Yep, the last part in my post was suggesting some ways we could determine if "item X was in the training data" (as well as some potential blockers for that from OpenAI's perspective.)