Re:Harvard’s new computer science teacher is a chatbot
by cdperera on Sunday June 25, 2023 @06:09AM
(#36466593)
Regarding providing hints, my university does this actually. The automated testing software we use (in house built, actually) allows the lecturer / TA team to define hints in case that test case fails.
Providing hints is a bit tricky, however. Often times, students fail the test case for unexpected reasons, and our hints actually mislead them. I've had students come to me (as a TA) saying that the test case is wrong because they take into account the hint.
Naturally, we could just give better test cases / give a broad disclaimer, which we try to. We do the latter, but the former is tricky, especially when we are trying to come up with novel problems.
Providing hints is a bit tricky, however. Often times, students fail the test case for unexpected reasons, and our hints actually mislead them. I've had students come to me (as a TA) saying that the test case is wrong because they take into account the hint.
Naturally, we could just give better test cases / give a broad disclaimer, which we try to. We do the latter, but the former is tricky, especially when we are trying to come up with novel problems.