I would guess the region would be distinct, as all the responses above are answering the question of how the model feels, but agree it’s an empirical question
as all the responses above are answering the question of how the model feels,
Sorry if I was unclear. By your “test prompt” I mean the prompt asking for the feelings of the model. So put through ordinary text (not attractor text) and then ask the question “Deeply feel into which part...”
Then see if these feeling outputs cluster distinctly. Also, it may be interesting to see a mapping of feelings outputs relative to (non-attractor) conversations by topic.
Thanks! The idea was to pick “ordinary” conversations for the 1000 conversations sample, however I’m sure those I picked aren’t representative of all AI conversations. So could definitely expand the scope of the conversations in various directions, if that’s what you mean?
I would guess the region would be distinct, as all the responses above are answering the question of how the model feels, but agree it’s an empirical question
Sorry if I was unclear. By your “test prompt” I mean the prompt asking for the feelings of the model. So put through ordinary text (not attractor text) and then ask the question “Deeply feel into which part...”
Then see if these feeling outputs cluster distinctly. Also, it may be interesting to see a mapping of feelings outputs relative to (non-attractor) conversations by topic.
Thanks! The idea was to pick “ordinary” conversations for the 1000 conversations sample, however I’m sure those I picked aren’t representative of all AI conversations. So could definitely expand the scope of the conversations in various directions, if that’s what you mean?