Why does it seem so hard to make training data for this? You can cook up a few thousands of training data and do an RLHF.
Yes, but all that does is locate "I don't know" near the cooked up data within the embeddings. This doesn't actually reflect an absence of data in the training.
alt Hacker News
Yes, but all that does is locate "I don't know" near the cooked up data within the embeddings. This doesn't actually reflect an absence of data in the training.