[sebzim4500]

>As long as it comes across some reasoning process that have not been seen before in the training wordset, which can be as easy as a middle school math question

Is this true even if you tell it to show its working? In my experience that drastically improves its ability to do math problems.

[Aperocky]

At the end of the day it's still a language prediction model.

Which means whatever apparent logic you're getting out of it is from text that it has learned. not reasoning embedded within those text, but the actual text itself.

[petilon]

It can't solve quadratic equations.

[sebzim4500]

Prompt: solve x^2 + 11x + 30 = 0. Show your working

Answer: To solve this equation, we can use the quadratic formula:

x = (-b +/- sqrt(b^2 - 4ac)) / (2a)

Plugging in the values for a, b, and c, we get:

x = (-11 +/- sqrt(11^2 - 4130)) / (2*1)

x = (-11 +/- sqrt(121 - 120)) / 2

x = (-11 +/- sqrt(1)) / 2

x = (-11 +/- 1) / 2

x = -5 or x = -6

So the solutions to the equation are x = -5 and x = -6.

[fnordpiglet]

That’s true of almost all humans too. You’re self selecting for the elite you belong to.

[roflyear]

Largely yes. Some prompts can make it better or worse.