An instructor at Texas A&M University misused AI to claim large parts of his class were cheating on assignments, imperling their degrees, the partner of a student claims.
Dr Jared Mumm, a campus rodeo instructor and teacher of agricultural classes, reportedly sent students an email on Monday informing large parts of his class they would be getting a zero on recent assignments because he tested their writing with “Chat GTP” and the AI programme claimed to have written them all.
(OpenAI’s landmark AI programme is called ChatGPT).
“I copy and paste your responses in [ChatGPT] and [it] will tell me if the program generated the content,” Dr Mumm wrote, according to the partner of a student in his class who spoke with Rolling Stone.
The instructor, when confronted with evidence from students that they had written their own papers, reportedly said, “I don’t grade AI bulls***.”
OpenAI, as well as outside observers, have noted that ChatGPT isn’t fully reliable at detecting when a text is written by AI. The programme can also be made, with little encouragement, to make entirely false claims, going so far as to fabricate primary sources, The Washington Post notes.
The Independent has contacted Dr Mumm for comment.
Texas A&M told PC Magazine it was aware of the issues in the class and is investigating.
“No students failed the class or were barred from graduating as a result of this issue,” the university said in the statement. “The professor is working with the students to determine whether AI was used to write their assignments and, if so, at what level.” The diplomas, however, will remain on hold until individual investigations are completed.
Powerful AI tools like ChatGPT have set off heated debates in academic circles about academic freedom, plagiarism, and fairness.
Some institutions, like the New York City public school system, have proactively banned such tools.
Others argue that AI can be viewed as another electronic aide in the classroom, like a digital academic database or a calculator.
