To test Pi as a brainstorming partner, I ask it to help me brainstorm research questions about contemporary anglophone Pakistani fiction with regard to world literature and postcolonialism.
Pi's suggestions are useful but seem a bit superficial.
I take one of Pi's suggestions to dig deeper and it hallucinates (i.e. making things up on its own).
One of the books Pi suggests does not even exist.
Pi's suggestions are useful but seem a bit superficial.
I take one of Pi's suggestions to dig deeper and it hallucinates (i.e. making things up on its own).
One of the books Pi suggests does not even exist.
Here is another example of the comparison between Pi and ChatGPT 3.5.
I tell both Pi and ChatGPT 3.5 that I have been shortlisted for an interview for a Fulbright scholarship.
Then I ask them about the kind of questions I could be asked during the interview.
Pi's suggestions are short and superficial while ChatGPT 3.5 responds like it really wants you to ace the interview.
That said, if I were running Pi, I wouldn't worry too much about it. A year ago ChatGPT answers lacked nuance too and see how exponentially the model has improved over a year.
I tell both Pi and ChatGPT 3.5 that I have been shortlisted for an interview for a Fulbright scholarship.
Then I ask them about the kind of questions I could be asked during the interview.
Pi's suggestions are short and superficial while ChatGPT 3.5 responds like it really wants you to ace the interview.
That said, if I were running Pi, I wouldn't worry too much about it. A year ago ChatGPT answers lacked nuance too and see how exponentially the model has improved over a year.
Loading suggestions...