## Saturday, December 17, 2022

### Coding with ChatGPT–Armstrong Numbers

Trying out ChatGPT seems to be all the rage these days in certain geek circles. I may even be late to the game but I tried a few things over the last couple of days.

I started with one of my favorite little projects. Armstrong numbers are a form of narcissistic  number which is a number that is the sum of its own digits each raised to the power of the number of digits. I first wrote a program to calculated these as an undergraduate when I wrote programs for it in about a half dozen different languages.

I fed in the following prompt using C#, Visual Basic, and Python as the programming language.

Write a [programming language] program to calculate three digit numbers were the sum of the cube of each digit equals the original number.

The results for C# and VB were the same algorithm written in the specific syntax. The Python code was slightly different. You’ll probably not be surprised that the code ChatGPT showed me is very similar, if not identical, to code examples you can find with Google or Bing.

The C#/VB plan depends highly on integer division and the modulus operator to break down the number into its digits.

for (int I = 100; I < 1000; I++)
{
int sum = 0;
int temp = I;

while (temp > 0)
{
int digit = temp % 10;
sum += digit * digit * digit;
temp /= 10;
}

if (sum == I)
{
Console.WriteLine(I);
}
}

The Python sample changes the integer into a string and used that to address the individual digits.

for num in range(100, 1000):
# Convert the number to a string so we can access each digit
num_str = str(num)
# Initialize a sum to store the sum of the cubes of the digits
sum_of_cubes = 0
# Iterate through each digit in the number
for digit in num_str:
# Convert the digit back to an integer and add the cube of it to the sum
sum_of_cubes += int(digit) ** 3
# If the sum of the cubes is equal to the original number, print it
if sum_of_cubes == num:
print(num)

Note that the Python example nicely includes comments. A dead giveaway that a student didn’t write it. All samples come with simple explanations of how the code works. The explanations tend not to be very deep so oral questioning of a student would probably still show if the student understood the code or not.

It looks like, for some simple, student exercises can be solved by ChatGPT. It is not much different from doing any other online search for the most part. How worried should teachers be about ChatGPT especially? I’m not sure. Cheating goes on all the time and there is a lot of sample code already out there for many common assignments. It’s going to be a bigger problem for educators who have very large numbers of students who can’t be familiar with the code their students write. Or who can’t ask them questions to make sure they understand what they turn in.

I think I would ask ChatGPT to solve some of my assignments before I assign them just so I know what sort of answers I might see.

Side note: Neither of the ways ChatGPT suggested is the way I solve this program. There are more than one ways to skin this cat.

#### 1 comment:

Unknown said...

Suppose you make the description a little more ambiguous? I haven't tried that, but wonder what the following would do:

Write a Java program dealing with Armstrong numbers. The program takes one or two command line parameters. If there is one parameter, print whether the value is an Armstrong number. If two values are given, they represent a range. Print all Armstrong numbers in the range.

Now the solver needs to at least look up what an Armstrong number is (good practice for student), and deal with ambiguity of two values being min/max or max/min order, open/closed interval. In the long run it's not whether the students create code unaided, but whether the result actually solves the problem. Real world problems often contain ambiguities which the student should ask about. This forces to read the resulting code and learn how to fashion good "queries" if they want help in solving the problem.