Tried, but it's not reliable. Tried in a few different scenarios, but I can't trust its results. You're doing great work, though! One day, it will surely be able to provide more accurate results.
This is amazing if it actually works as promised and is probably something even OpenAI would like to have (and potentially buy from you).
Could you share a bit of the behind-the-scenes magic? I know this is an open area of research and part of it involves actually having an equivalent of a “cryptographic blueprint” of the model itself, which obviously, as outsiders we don’t have… so really really curious.
*praying to god that the answer isn’t that you’ve trained a classifier on GPT’s generated outputs*
