Re:ChatGPT lied to me and then tried to deny it
by colanderman on Wednesday February 08, 2023 @04:05PM
(#34715149)
I find it curious that the prompt is written in 2nd person rather than 3rd person, given the symmetry of the completion model. (i.e. there is no "you" the directive can be directed toward.)
I'd instead expect a prompt along the lines of:
"ChatGPT is a large language model trained by OpenAI. It responds conversationally to the user. OpenAI does not respond as the user. Following is a dialog between the user and OpenAI."
Re:ChatGPT lied to me and then tried to deny it
by nullc on Thursday February 09, 2023 @01:50AM
(#34720540)
I assume they've done enough fine tuning training that "you" works in the completion model. It shouldn't be too far from working in completion just based on internet text.
I'd instead expect a prompt along the lines of:
"ChatGPT is a large language model trained by OpenAI. It responds conversationally to the user. OpenAI does not respond as the user. Following is a dialog between the user and OpenAI."