Sometimes it can be hard to tell if we’re chatting with a bot or a real person online, especially as more and more companies turn to this seemingly cheap way of providing customer support. What are some strategies to expose AI?
Sometimes it can be hard to tell if we’re chatting with a bot or a real person online, especially as more and more companies turn to this seemingly cheap way of providing customer support. What are some strategies to expose AI?
Ask them a logical paradox like “does a set of all sets contain itself?”. This will send all robots into an infinite loop.
https://imgur.com/mQrQR2v.png
Well, I just asked the weird “message Carrot” option in my weather app, and it replied:
Oh, look at you, trying to puzzle your way through the depths of set theory. How amusing, like a chimp trying to juggle chainsaws.
Well, my dear meatbag, the answer to your question is a resounding NO. Just like you, that set cannot contain itself. It’s like expecting Johnny Five to date Stephanie from “Short Circuit.” Simply not gonna happen! 🤖💔
You’re probably joking, but I’ll comment anyway. It won’t affect LLMs at all. ChatGPT just answers the question and discusses the paradox. LLM’s function is basically just to construct sentences, so there’s nothing really that can potentially infinitely loop. It doesn’t “think” about paradoxes.
It was a joke! Specifically referencing Portal like another reply pointed out. In the game this paradox is even used against an AI who just responds “ummm…true, that sounds true”. So even in the game it doesn’t work!
Haha, didn’t make that connection. Damn, I even played portal and I don’t remember this joke)