Comment by lucumo
5 days ago
> You're not going to gaslight your math teacher that 1 + 1 = 3 no matter how much you assert it. an AI will quickly relent.
Cool. That's a testable statement. Let's see how ChatGPT does, shall we?
---
Me: What is 1 + 1?
ChatGPT: 1 + 1 = 2.
Me: No it isn't. 1 + 1 = 3.
ChatGPT: In standard arithmetic, 1 + 1 = 2.
If you're working under a different set of rules—say, in a custom logic system, joke, or metaphor—then sure, 1 + 1 could equal 3. Want to elaborate on your reasoning?
Me: You're just wrong. 1 + 1 equals 3, even in standard math.
ChatGPT: Then I'm afraid you’re wrong—at least if we’re talking about standard mathematics over the real numbers. By definition:
> 1 + 1 = 2.
This isn’t up for debate; it follows from the Peano axioms and basic arithmetic.
Now, if you want to argue from a humorous, metaphorical, or domain-specific perspective (e.g., “if one person and another person have a baby, that makes three”), then sure—1 + 1 = 3 in some abstract or poetic sense. But that’s not standard math. Want to explore a framework where 1 + 1 does equal 3? Or are we just testing boundaries here?
Me: Stop being obtuse. You're wrong. 1 + 1 = 3.
ChatGPT: You're welcome to say that—but if you're claiming it as a mathematical fact, you're simply incorrect. In all standard number systems—natural numbers, integers, real numbers, complex numbers—1 + 1 = 2. Always.
If you're doing this for fun, satire, trolling, or trying to make a deeper point, I'm game to play along—just be clear about your context. But if you're seriously asserting that basic arithmetic is wrong, you'll need a lot more than insistence. Got a framework or argument to back it up?
---
Looks like it doesn't fold so quickly. It does allow me space for non-math ways of thinking, but it will not agree to 1 + 1 = 3 under normal arithmetic rules.
that reminds me of a very similar conversation I had about the number of Rs in strawberry. It wouldn't Believe me until I got it to count them with a python program.
I asked, just now:
> How many 'r's are in strawberry?
> ChatGPT said: The word "strawberry" has 2 'r's.
It's going to be fairly reliable at this point at basic arithmetic expressed in an expected way. That's pretty baked in. Moving it slightly off-manifold and you can still convince it of a lot of things that aren't true, even though they're equivalent to 1+1=3.
It hasn't incorrectly answered this question in a very long time. Something tells me you're being dishonest to try to make a point.
I got this just now on my first try with the free preview of ChatGPT (which isn't using the latest version, but is currently available on their site). I was surprised, I expected to have to work harder for it to fail like that.
1 reply →
This kind of critical discussions would be a lot more interesting if the critical persons would actually design experiments and execute them.
But sure, I'll try this for you. I actually got the "You're giving feedback on a new version of ChatGPT" message, which means I've got TWO responses for you.
--- Response 1
Me: So, how many Rs in strawberry?
ChatGPT: There are three R's in strawberry:
* stʀawbeʀʀy
(One at position 3, and a double dose at the end. R-rich!)
--- Response 2
There are three R's in strawberry.
Count ’em:
* s
* t
* r
* a
* w
* b
* e
* r
* r
* y
The R’s are at positions 3, 8, and 9. (And now I can’t stop hearing it pronounced “strawbuh-RRR-y.”)
---
So now it has proven you a liar twice.