Can ChatGPT Solve this Math Riddle?

Testing ChatGPT on High School Math Puzzle

Itā€™s a beautiful Saturday morning, perfect for ChatGPT and math puzzles!

Problem Statement

Hereā€™s the problem statement:

(weā€™re going to ask ChatGPT to solve the puzzle above)

But first, letā€™s talk about the solutionā€¦

When you get to sin(Pi), do you assume itā€™s a variable or a value?

Youā€™ve probably never seen a variable named Pi.

Youā€™d treat Pi as a value.

This makes sin(Pi) = 0 and therefore the whole product equals zero.

The correct answer is 0.

But can ChatGPT figure it out?

Hereā€™s a youtube version of this post:

Naive Prompt

Fail.

ChatGPT canā€™t answer the problem without specific values for the angles.

Chain of Thought

Similarly, ChatGPT insists it canā€™t solve the problem without specific values for the angles.

Plan and Execute

What if I ask ChatGPT to create a plan first, then follow the plan?

Still no luck!

Agents

Here I try pseudo-agents.

Not really agents, but agents in spirit.

I ask ChatGPT to solve the problem, review the solution (i.e. give feedback), then solve it again using the ā€œfeedbackā€ from step 2.

Honestly, surprised that didnā€™t work better!

The professional mathematicianā€™s review didnā€™t add much value. Overthinking it, ChatGPT!

Give a Hint

Now I nudge ChatGPT to think about each multiplier in the problem statement and whether any multiplier is zero. This is a pretty big hint:

It seemed promising:

ā€œSo, we should check if any of the angles is a multiple of pi. If at least one angle in the set ā€¦ is a multiple of pi, thenā€¦ [answer is] 0ā€

But the answer just stopped there.

ChatGPT failed to proceed to check if one of the angles is a multiple of pi.

Give Another Hint

Letā€™s make it even more explicitā€¦

Hmmā€¦

Why isnā€™t ChatGPT writing out each multiplier, like I ask it to?

Force Expansion

Ok, Iā€™m going to be as explicit as possible.

ChatGPT: write out each multiplier, without ellipsis, then solve the problem.

I throw in Chain of Thought too.

This is the only prompt Iā€™ve tried so far that gives both the correct answer and correct explanation:

ChatGPT listed out the Greek alphabet.

Then, ChatGPT explicitly wrote out the product.

It noticed pi is one of the angles in our product.

Hence, the product ā€¦ is zero. 

Nice work, ChatGPT!

Really glad I wonā€™t have to sit here all day šŸ«  

BUT it feels like I had to give overly specific instructions for ChatGPT to finally get it. I donā€™t want to have to do that.

Easier ā€˜Solutionā€™ ā€” Give More Context

Seeking a shortcut with less handholding, I try giving ChatGPT some context:

ā€œSolve the following riddleā€

The answer is correct but reasoning is flawed:

ā€œomega, which is a multiple of piā€

I donā€™t know why it assumes that.

But at least the answer is correct, with minimal hand-holding from me!

My hypothesis:

Using ā€œriddleā€ makes ChatGPT more certain that there is a definitive answer.

I run it again:

Correct answer and correct explanation!

Again:

Correct answer and I think correct explanation. ChatGPT says ā€œpi is typically included in such series to indicate completenessā€ which is a bit vague. But Iā€™ll take it.

Out of 3 runs with the ā€œriddleā€ context, ChatGPT got it right 3 times.

But its reasoning was a bit shaky that first run ā€” ā€œomega which is a multiple of piā€.

It seems like contextualizing this problem as a ā€œriddleā€ forces ChatGPT to produce an answer rather than give a generic solution.

Changing ā€œRiddleā€ to ā€œProblemā€

Now I change ONE word.

ā€œRiddleā€ to ā€œproblemā€.

Back to wrong, generic answers.

Keep the Riddle, Change SIN to COS

Iā€™m curious what effect the word ā€œriddleā€ has.

Letā€™s change sin to cos and see what happens.

Itā€™s no longer 0.

Not much of a riddle, but letā€™s see what ChatGPT says.

Seems like the term ā€œriddleā€ forces it to look for a closed-form solution.

I like this output even more because ChatGPT says it needs more information AND tries to come up with a plausible answer for the riddle.