alt Hacker NewsIt could be trained to say that, but it's not exactly clear how you would reinforce the absence of certain training data in order to emit that response accurately, rather than just based on embedding proximity.
Replies
jsnider3 • 05/15/2025
Seems easy. Have a set of vague requests and train it to ask for clarification instead of guessing.
➕ show 3 replies
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.