# How would an AI work out this question?

I am trying to create an AI that makes reasonable guesses at truths of statements. However...

Human: "Prove that no number exists which is one more than a billion."

AI: "Is it true for the number 1? No. I am 1% sure the statement is correct."

AI: "Is it true for the number 2? No. I am 2% sure the statement is correct."

...

AI: "Is it true for the number 999,999? No. I am 99.99% sure the statement is correct."

AI: "Having tested a large number of examples. I conclude that the statement is correct."

Human: "The statement is wrong: one billion and one."

What do you think has gone wrong?

• I believe that the whole reasoning is wrong. The fact that his certainty increases with the number is also weird: it is like the higher the number the more certain the AI is, which makes no sense. Furthermore, there's also the problem of not being able to generalise.
– nbro
Jul 23, 2019 at 20:16
• The AI didn't try to disprove it... it hadn't "understood" the misleading question to a level where it could find the fastest route to a disproof (or proof). Disproof may be a missing strategy. Jul 30, 2019 at 15:04