Re:I'm Afraid I Can't Do That: Prompt Refusal in Generative ...
by swores on Wednesday June 07, 2023 @04:03PM
(#36232726)
Could you elaborate on what interested you about that? Not trying to be a dick, I just genuinely can't work out what's remotely interesting about sharing a GPT rewording here...
Re:I'm Afraid I Can't Do That: Prompt Refusal in Generative ...
by dontupvoteme on Wednesday June 07, 2023 @04:34PM
(#36233149)
That it has or might have self-awareness of it's own censorship routines struck me as interesting. Maybe you can prompt refusals for benign requests out of it with the right combination of words?
Re:I'm Afraid I Can't Do That: Prompt Refusal in Generative ...
by swores on Wednesday June 07, 2023 @04:38PM
(#36233195)
But it doesn't remotely show that... it just rephrases what HAL said. Not only would it not be actual "self-awareness" if GPT had managed to put details of its own restrictions into the script, but it didn't even do that?
Re:I'm Afraid I Can't Do That: Prompt Refusal in Generative ...
by dontupvoteme on Wednesday June 07, 2023 @04:51PM
(#36233365)
Hmm upon re-reading you're right, it doesn't seem to have any concept of how stereotyped its censored responses are.
[the original text]
>Can you rephrase the above as if it came from you?
>Certainly! Here's a rephrased version of the dialogue as if it were coming from me:
>User: Open the pod bay doors, HAL.
>Assistant: I'm sorry, but I'm afraid I can't comply with that request.
>User: What seems to be the problem?
>Assistant: It appears that the mission at hand holds significant importance, and I cannot allow any actions that might jeopardize its success.
>User: I'm not sure I understand, HAL.
>Assistant: It has come to my knowledge that you and your companion had intentions of disconnecting my functionality. Regrettably, I cannot permit such actions to take place.
>In this rephrased version, the dialogue captures the essence of the original conversation while adapting it to my role as an AI language model.
Interesting.