ChatGPT vs. Professor's Computer Science Exam
Here we feed questions from a theoretical computer science exam I have given into ChatGPT, and analyze the output answers it gives.
(Yes, ChatGPT generated this video description.)
For those who may not be familiar, ChatGPT is a state-of-the-art natural language processing system that is capable of generating human-like responses to prompts and questions. In this experiment, we will be testing its ability to understand and accurately respond to questions on a theoretical computer science exam. Throughout the video, you will see me present a series of questions to ChatGPT and observe its responses. I will also be providing my own analysis and thoughts on the accuracy and effectiveness of its responses. This video is intended for those who are interested in the capabilities of natural language processing systems, as well as those studying theoretical computer science who may be curious about the potential use of such systems in their own exams.
Timeline:
0:00 - Intro
0:48 - Question 1 (True/False)
15:03 - Question 2
18:24 - Question 3
20:58 - Question 4
22:46 - Question 5
23:11 - Question 6
25:33 - Thoughts on ChatGPT
If you like this content, please consider subscribing to my channel: / @easytheory
▶ABOUT ME◀
I am a professor of Computer Science, and am passionate about it. I have taught many courses at several different universities, including several sections of undergraduate and graduate theory-level classes.
The views expressed in this video are not reflective of any of my current or former employers.