alt Hacker NewsNo amount of prompt engineering will give you the true probabilities for the model producing a certain response; this is something you can only get by inspecting the internal state at inference time.
Replies
weird-eye-issue • yesterday at 6:58 AM
For most use cases is that actually needed though? Just having it choose between predefined responses seems like enough but I'm curious about specific use cases because I do feel like I'm missing something
➕ show 3 replies
Does this give you the true probabilities for a certain response either? How does it work exactly? The probability of an overall positive answer isn't just the probability that the next token is "Yes"