I wonder if, without any meaning to assign to your bot’s blurbs, GPT found its own, new meanings? Makes me worry about hidden operations....
Are you suggesting that somehow the LM was able to notice a connection between two parts of my identity I had intentionally kept separate, when it wasn’t specifically trained or even prompted to look for that?
I wonder if, without any meaning to assign to your bot’s blurbs, GPT found its own, new meanings? Makes me worry about hidden operations....
Are you suggesting that somehow the LM was able to notice a connection between two parts of my identity I had intentionally kept separate, when it wasn’t specifically trained or even prompted to look for that?