alt Hacker News>I challenge you to give it even a simple, but original, problem to solve.
(34903173/x)+(238 * 2650) - 323326 = 45323434, solve for x
Statistically, no one has ever done this calculation ever before. It's entirely unique.
O1 answered "x = 34,903,173 divided by 45,016,060", which is correct.[1][2]
Now I guess you can pick up the goal post and move it.
[1]https://chatgpt.com/share/6709481a-3144-8004-a7fd-0ccd9e3bc5...
[2]https://www.wolframalpha.com/input?i=%2834903173%2Fx%29%2B%2...
Replies
My brother in christ, how is
A/B + C*D - E = F, solve for B
It's the same as with coding by the way: it can reshuffle things it has already seen while changing variable names and so on. Ask it something which is not in stackoverflow or geeks4geeks and it goes tits up.
PS: Tested it on GPT 3.5: same answer.
> Now I guess you can pick up the goal post and move it.
The central problem with math is that you have an infinite amount of space within which to move these goalposts.
How many variants on this trial before we find a mistake?
What is an acceptable error rate?