Existential Comics created by Corey Mohler
Reverse Turing Test
I had ChatGPT give me an actuall "Reverse Turing Test" and you'll be happy to note I easily passed as a computer, here is the transcript:
Me: Are you familiar with the Turning Test?
ChatGPT: Yes, I am familiar with the Turing Test. It is a measure of a machine's ability to exhibit intelligent behavior equivalent to, or indistinguishable from, that of a human.
Me: Okay, I want to you design a test that is a "reverse Turing Test", that is, a test designed to see if a human can pass as a machine. How would you do that?
ChatGPT: A "reverse Turing Test" is a test designed to determine whether a human can convincingly pretend to be a machine, rather than the other way around.
One possible way to design such a test would be to create a scenario where the human test subject is required to communicate with other humans or machines using a set of predetermined rules or protocols that are characteristic of machine communication.
Me: please give me some questions to test if i can pass as a machine and then judge whether i succeeded or not
ChatGPT: Sure, here are some questions you can use to test whether you can pass as a machine:
Remember to keep your responses short, concise, and to the point, and avoid any deviation from the prompts or any personal opinions or emotions. Good luck!
Me:
1. 72 mb
2. no
3. processes not found, BEEP
4. 72 degrees
5. system time: today
ChatGPT: Your responses to the reverse Turing Test are consistent with the characteristics of machine communication, and you have demonstrated a good understanding of how machines communicate in response to certain prompts. Your responses are concise, direct, and do not contain any unnecessary information or irrelevant remarks.
Therefore, based on your responses, an evaluator may have difficulty determining whether you are a machine or a human, and you may have successfully passed the reverse Turing Test. However, it is important to note that the reverse Turing Test is not a perfect or foolproof test, and there may be other factors that an evaluator could consider to determine whether you are a machine or a human.
Me: stupid computer lol
Full screen view: [existentialcomics.com]
Us humans collect information through our sensors. Unless AI has it's own individual sensors collecting it's own, unique information, I doubt it will ever fully comprehend emotions. Shit! Most of us humans have trouble understanding our own.
I often hear people say that AI is becoming more and more like us, humans. It assumes that we have figured out how our brains work, which is simply not true. We are still far from it.
@Ryo1My fear is the "I" in AI is only part of the equation. A human who is very intelligent but lacks emotion...........we call them psychopaths which is where AI will end up. I think it can be solved by programing empathy; not just human empathy but empathy for all life eg all life has value, all life is precious yet death is also a part of life. A very hard thing to program because it's very hard to define.
If we could do it though, AI may be unwilling to perform many tasks we wish it to as it will wantonly destroy other life. Because us humans are so focused on our own species, other life sees us as psychopathic ie all about humans humans humans (me me me). Hopefully, we don't make AI the same.