I'm a human.
The model needs to reply with something and here it tells the user the assumptions it made. The only alternative I can think of would be to arbitrarily choose two Bostons but my guess is it is more likely that people making this request would intend to include the same location in both.
One use for ChatGPT is to give a prompt with lists of data. It is convenient if ChatGPT handles the trivial edge cases correctly so that the user doesn't need to do preprocessing.
"Can you give the distance in miles between a list of pairs of cities? Want the output formatted like this:
city a, city b, 10
city b, city c, 100
...
The pairs of cities are:
New York City, Los Angeles
Chicago, Los Angeles
Chicago, Paris
Chicago, Boston
Boston, Boston
Boston, Los Angeles"
Response from ChatGPT:
"Sure! Here is the list of pairs of cities and their distances in miles:
New York City, Los Angeles, 2,798
Chicago, Los Angeles, 2,054
Chicago, Paris, 4,973
Chicago, Boston, 1,099
Boston, Boston, 0
Boston, Los Angeles, 2,905
Please note that these are approximate distances and may vary slightly due to factors such as route taken and Earth's curvature."
me again: if it asked you to clarify exactly which city you are referring to for each without making assumptions, making requests would be pretty tedious. Sometimes, you are processing data that starts out ambiguous to you anyway.