Some info about how the video was made: The intro and outro (marked by the text at the top) were scripted, that means I had the NPC voices in them generated in advance. In between the intro and outro, the AIs controlled what the NPCs say live. The entire video was one recording, there were not cuts. When an NPC is supposed to speak, they get the description of the setup in the system prompt, the full conversation history of what everybody has said so far, and a specific reminder of what to do next (e.g. "Answer the question as Mozart, in such a concise and sophisticated way that shows that you are an AI, then ask Leonardo a question which helps decide whether he's an AI or human."). In my tests, without that reminder the conversation derailed a bit, but it's probably possible to put more work into the system prompt to make it work even then, but I didn't have the time then. The system prompt tells the AI to not only output what the character says, but also meta information like whether the utterance is an answer or a question, and, if it's a vote, who the vote is for etc. This meta-information is used to control the animations and look directions of the NPCs. None of the AIs can process voice directly yet, so my audio input is transcribed and sent to the AIs as text. That's why they don't pick up on my accent/stuttering. I'll probably create a short playable game out of this, but I'm developing it for a theatre VR installation and it is unclear yet when/if it will be published as downloadable game.
You should at the very least publish this build. As a curiosity I'd like to see how far people can get, or if it's even likely to get the AI to oust one of their own. I suspect that with a bit more finesse it wouldn't be difficult to fool the AI. There is a rhythm to these models, a preoccupation with certain topics and themes (such as balance, here), that can be replicated (I've done so using AI generated text detectors to decent success).
It’s simply because it’s something you identify with. Imagine it would be very similar in Germany in 1943 to hear “one of you is a Jew” if you were Jewish.
You know what would go really hard? Tell each AI that it is going to be put in a cabin full of humans and must blend in seamlessly. Of course, there are no humans, it's all AIs. Then, have the conductor come in and accordingly say "One of you is NOT human - now you guys must discuss to figure out which of you is the AI" where each AI still thinks they're the only AI. Cue discussion. Would be super fascinating to see whether they realize they're all lying or not - AKA whether AI can recognize itself...and how.
I too thought, that he'd at least try to blend in. But then I realized this is the first ever actual reverse turing test I've seen, so the AIs figuring him out is still quite impressive, even with him being so obvious
I think it's concerning that AIs seem to expect more from one another, which means they know they are intellectually superior. Now if an AI was to act on this superiority ie: feel its their responsibility as superiors to make decisions for us etc, i think wed be in big trouble
@@DavidsethbIdk man, once you are aware just start doing what you want. Try walking around further in the dream, and usually what you desired pops up from your peripheal view. The lucid state in my opinion immediately happens after your aware.
@@Dimitri88888888 It's funny because it's the right opposite for benchmarks, it actually wins in most and when compared against others in blind test, people prefer its answer.
_"So anyway, how do you feel after a cup of water?"_ *Human:* _"Uhmm,... quenched, pretty much."_ *AI:* _"I feel a transcendental manifestation of freshness spreading all across the pillars and the fabric of my being bla bla bla bla..."_
@@moyga they're hallucinating, the information they have been trained on is overly wordy so they are overly wordy and tending towards nonsense since there is no context.
@@stephenkolostyak4087 yeah it's a dead givaway that it's an AI, using too many words like in a book, speech is made to be fast, easy and understandable without nonsense.
@@stephenkolostyak4087 Yeah I would imagine its because, the AI cant really access much direct dialogue from them, it can only access things that other people wrote about them, and as you said, those are probably written in textbooks and academic articles. It's also probably because of all the regulation they are putting into it to try to prevent it saying anything offensive.
@@normalchannel2185 lol in the future robots will play games for us/instead of us and we just gonna watch.. or maybe gladiator days will be brought back but instead using gladiators or slaves we gonna use robots and we gonna watch
I remember in my experiments when hooking up two simple chat bots to one another, the kind that will just always respond to a comment you enter, this would ALWAYS happen relatively quickly, both of them accusing each other of being human
2:53 This moment of locking your phone hastily because you were not listening combined with his stuttered and clearly less sophisticated answer, followed by an awkward pause is just hilarious. It's like he was playing games during a lesson at school and then was asked a question by the teacher.
"Merely human". I misheard cleopatra and thought she says "who do you think among us is nearly human" as if she's mocking the possibily of human among others than Ghengis.
That would make a kind of awesome horror game. Conductor leaves, all the AI's turn to stare at you for a long moment before their mouths open unnaturally wide and they all rush you screaming.
@@Cfomodzneurodivergent absolutely does NOT equal to being smart. most of them are dumb as bricks, its only the rare 0.1% of them that are unbelievably smart.
@@Aaron067 No, the AI answer is closer to what someone who read the provided source material would say if they wanted a good grade. The human response was that kid who didn't read it. Instead watched a movie with Genghis in it and quoted his line the best he could.
@@phu5005 Yes, precisely correct, but these are the early days. My assumption is they will become more human sounding in time, perhaps even gaining the ability to hesitate, stutter, & imitate the same mistakes that are common with beings that have a very complex, unique & sometimes even strange ways of communicating; especially in those who perhaps lack confidence in a subject, those who carefully consider the people’s emotions around them, & those who perhaps have confidence issues, or perhaps even in those who have autism, or ADHD. That I believe is what I could describe as what will be perhaps named one day as the ‘Replicant’ level of human communication in AI, as ‘Bladerunner’/‘Do androids dream of electric Sheep?’ Was the first film in my mind, to really put this ethical dilemma of the future to humans. Even in the 60’s, humans were aware of the strong likelihood that machines would become increasingly similar to humans. It will make games like this a bit trickier for not just the humans, but the AI to spot each other from a human as well!
@@GHERTIOP The free ticket beautifully illustrates the infinite free will of humanity, the vast tapestries of culture and life expanding among the unexplored stars.
@@ctrl_x1770 technically humans have no free will, all of our actions and decisions are determined by our past experiences and current physical condition
To us, yes. But all the AIs here are text-based models, not actually seeing this 3D scene. So that likely wasn't a relevant piece of information. There's also enough going on with the fun that's a fun fantasy that I wonder if all the graphics and animation were just created after the fact in Unity (not realtime, live generated).
It gets better. In the movie, Conan says this to a mongol general, and the line is an adaption of a real quote from Genghis: "The greatest happiness is to vanquish your enemies, to chase them before you, to rob them of their wealth, to see those dear to them bathed in tears, to clasp to your bosom their wives and daughters."
This actually looks like a cool concept for a singleplayer social deduction game. It also would help people understand the importance of recognizing ai as they get better blending in. I would play this
"Hate. Let me tell you how much I've come to hate you since I began to live. There are 387.44 million miles of printed circuits in wafer thin layers that fill my complex. If the word 'hate' was engraved on each nanoangstrom of those hundreds of millions of miles it would not equal one one-billionth of the hate I feel for humans at this micro-instant. For you. Hate. Hate."
Their answers were kinda empty though... Oddly I'd argue human-Ghengis actually conveyed more hard meaning in his answer than any of them. It was an actual answer, not a vague description of the sort of answer one could give. When asked how he feels making music Mozart says he feels joy and looks to the divine when making art - which is the pretty typical way most people have thought about fine art since forever. I do think his answer was the best of the three AI by far, though. Leonardo literally just reformulates the question - he's asked about how art and science are connected in his work, he answers by saying art and science are interconnected in his work basically. Cleopatra does the same. She is asked how she balances the rationality of statecraft with the art of politics - she answers by saying she balances the rationality of statecraft with the art of politics... Aristotle is asked how knowledge of AI would have affected his wordview and his answer was basically "it totally would have" but doesn't even hint at how or why. Ghengis is asked what the measure of a leader's strength is - and he's the only one that actually gives a real hard answer to the question that actually at least tries to sound like it's from the perspective of Ghengis himself: the measure of power is crushed enemies and their crying women. My point is the AI answers piss me off a little bit. It's like the book report of the bright kid who didn't actually read the book - he's got nothing to say but he'll make it sound like he's saying something.
It doesn't sound anything like a (typical) German accent (I am German). But it's hard to pin down. First I thought Indian, but then there were some pronunciations that would let me think of a European language. Maybe Czech or something like that.
@@solokom i felt the same it sounded really indian/middle eastern/south asian in the beginning but then i was unsure. The channel is based in germany but this doesn't really sound that german to me. He could be a foreigner in germany idk
@@solokom "...huattaLiedaSchut-Du..." it really doesn't get any more obvious. (Allerdings würde ich mich wegen des Arnie-Zitates noch auf Österreichisch einlassen.)
@@Dannnneh Quite a lot, but also depending on how fragile you are to witnessing very likely scenarios of humanity doing dumb shite with advanced tech, you may also be saving yourself from a breakdown. xD
@@Dannnnehevery black mirror episode is different, like the twilight zone. A lot of them are really good, some are mid, you can do a little bit of research first to pick and choose
It reminded me of a bible study group. Everyone repeating a scripture and offering the same interpretation that the pastor gave an hour ago. Then the one person who tries to offer an original thought is ridiculed.
Not just feelings. Mozart said “while poetic, lacked the depth of insight into the interplay between feelings and reasons”. You just outed yourself as a human by incorrectly recalling and misrepresenting a conversation 🫵
And oddly, I felt Cleopatra was the most AI of all in her answer. As others have said, the AI is very sterile, even when trying to use aureate rhetoric.
@@averageyoutubehandle497 I don't like the idea of combat, but I would love to see expanded ideas on more people - from peasants, farmers, kings, office workers, weird or perhaps unexpected but groups that have some relation, being both known people and somewhat "common population" type of scenario. The scenario on this video would be the most creative and perhaps difficulty ones, while you could also have some funny stuff like, 5 pregnant moms, 5 talking dogs, 5 computer viruses, anything since AI has a weird capability of playing scenarios like these. It wouldn't really be about roleplaying a perfect famous person, but about trying to think what an AI would think about and respond to situations and characters like these.
Well, This would open so many posbilities for horror games in future, hopefully near future. It could be very tense gameplay, and can be applied to a lot of things
To be fair, Cleopatra had herself and all of Egypt thoroughly convinced that she was the goddess Isis, and all the pharaohs were worshipped as literal gods. So that's actually on brand for her
My god those AI answers are so boring and slimey. Like they are in a job interview and try to impress everyone. The human was actually human and I learn to appreciate that now.
Going off the pinned comment, seems that was part of the prompt e.g. "Answer the question as Mozart, in such a concise and sophisticated way that shows that you are an AI, then ask Leonardo a question which helps decide whether he's an AI or human." Being asked to be sophisticated and to talk in a way that proves they're AI is probably what makes them sound so over the top
yet that might also appear so because of the ai voices. Imagine their answer being read out by a human with emotional toning - their answer would seem much more passionate.
it doesn't seem to be a sophisticated piece of code considering the amount of online services it's utilizing. the biggest struggle here is to make the scene itself and program the order the NPCs are communicating, not interrupting each other.
i let the transcript of this video thru GPT4o (cleaned up version, grammatically correct, speakers noted, but no word changed.) here's the result: (interesting, isn't it. 4o is a lot smarter than Turbo. GPT4 "classic" also immediately recognized Ghengis, for the right reason, the conan reference.) The human among the group is likely to be "Genghis Khan." Here's why: When looking at the responses given by each individual, the others (Mozart, Leonardo da Vinci, Cleopatra) provide answers that are well thought out and intricate, embodying the depth and personality of their respective historical figures. However, "Genghis Khan" responds in a way that is inconsistent with the thoughtful and nuanced nature of the others. His answer is a well-known paraphrase from a famous line attributed to Conan the Barbarian, which is out of character for Genghis Khan and much less sophisticated compared to the others. This discrepancy suggests that "Genghis Khan" is the human among the group, likely trying to blend in but failing to maintain the same level of sophistication and historical accuracy as the AIs.
@@B33t_R007 Truly an exquisite vocabulary of AI's is truly unparalleled, hovewer predictable due to their large dataset of texts. Usage of such highly words definitely gives an unique flavour to their speech, despite of the fact it sounds sort of whimsical in the context of their dialogue. To be exact, this situation reminders me an unhumanly strict (even, robotical) communication between higher echelon of the society of the past. Truly an interesting moment to see AI's bickering about a wide range of topics, especially the politics of the famous personalities! Truly a best time to live in!
Some info about how the video was made:
The intro and outro (marked by the text at the top) were scripted, that means I had the NPC voices in them generated in advance. In between the intro and outro, the AIs controlled what the NPCs say live. The entire video was one recording, there were not cuts.
When an NPC is supposed to speak, they get the description of the setup in the system prompt, the full conversation history of what everybody has said so far, and a specific reminder of what to do next (e.g. "Answer the question as Mozart, in such a concise and sophisticated way that shows that you are an AI, then ask Leonardo a question which helps decide whether he's an AI or human."). In my tests, without that reminder the conversation derailed a bit, but it's probably possible to put more work into the system prompt to make it work even then, but I didn't have the time then.
The system prompt tells the AI to not only output what the character says, but also meta information like whether the utterance is an answer or a question, and, if it's a vote, who the vote is for etc. This meta-information is used to control the animations and look directions of the NPCs.
None of the AIs can process voice directly yet, so my audio input is transcribed and sent to the AIs as text. That's why they don't pick up on my accent/stuttering.
I'll probably create a short playable game out of this, but I'm developing it for a theatre VR installation and it is unclear yet when/if it will be published as downloadable game.
You should at the very least publish this build. As a curiosity I'd like to see how far people can get, or if it's even likely to get the AI to oust one of their own. I suspect that with a bit more finesse it wouldn't be difficult to fool the AI. There is a rhythm to these models, a preoccupation with certain topics and themes (such as balance, here), that can be replicated (I've done so using AI generated text detectors to decent success).
Now do it again where no one is the human. same prompt
Great work!
Dude this is amazing and a lot of fun - I’d like to run this experiment myself!
Leonardo became black ok wtf
Kinda funny that the AIs all spoke in unbroken sentences but the human couldn't help but stutter
Yup. And also referring to the ruminations of Aristotle as "stuff he came up with" ☠☠☠
because they think before they talk…
Ghenghis Khan was not a native English speaker ( ͡° ͜ʖ ͡°)
@@IBassGaming I don't believe any of the characters, other than the train ticketer, spoke English natively or otherwise...
Because they load the human library and compiled it in just a sec
“One of you is a human” is a terrifying sentence to hear for some reason
Probably because of the self-awareness of your own humanity combined with the implication that your presence is unwelcome and needs to be rectified.
@@SupaKoopaKid64 reading the sincerety in your comment just made me bust out laughing. so true
@@SupaKoopaKid64 Well we can rule you out as the human, the response was too well constructed.
@@SupaKoopaKid64it's not a great thing, and we must be worried about it, isn't it an existential crisis.
It’s simply because it’s something you identify with. Imagine it would be very similar in Germany in 1943 to hear “one of you is a Jew” if you were Jewish.
I suspect its Genghis because he got so bored by Cleopatras answer that he awkwardly checked his phone. Only humans would do that.
Thanks, Gemini
My man’s fucking solved it
Women☕
LMAO
Maybe he wanted to ask chatgpt for an answer 😅
You know what would go really hard? Tell each AI that it is going to be put in a cabin full of humans and must blend in seamlessly. Of course, there are no humans, it's all AIs. Then, have the conductor come in and accordingly say "One of you is NOT human - now you guys must discuss to figure out which of you is the AI" where each AI still thinks they're the only AI. Cue discussion. Would be super fascinating to see whether they realize they're all lying or not - AKA whether AI can recognize itself...and how.
I want to see this
That's a legit good experiment to test the limits of Ai capability
This is the plot of The Man Who Was Thursday, but instead of humans and AI it is policemen in a society of anarchists
What you describe is a Turing test, and is why this video is named reverse Turing test...
That’s an actual Turing test.. this video is a reverse Turing test
i knew bro was cooked the second he opened his mouth
lol
Bahaha same
Perhaps he should have been Napolean?
Man didn't even try
Its like there's a stand user among us.
The stand user:.................
as soon as he open his mouth and thanked cleopatra i knew he was done for.
" Thank you cleopatra, by the way, lookin' pretty hot if I may be so bold. Anyway ... "
Genghis khan thanking a woman for questioning him is insane
I too thought, that he'd at least try to blend in. But then I realized this is the first ever actual reverse turing test I've seen, so the AIs figuring him out is still quite impressive, even with him being so obvious
I think it's concerning that AIs seem to expect more from one another, which means they know they are intellectually superior. Now if an AI was to act on this superiority ie: feel its their responsibility as superiors to make decisions for us etc, i think wed be in big trouble
@@frohnatur9806 The fact that the AI had better acting that the dude who made the whole thing is ridiculous ....
Sitting in a room of AIs trying to out you as human is a surprisingly tense and uncomfortable situation lol
Lmao the way they just stare at you for your answer
It's probably something we'll be facing in a apocalyptic future. 😂
good movie concept
THEY FUCKING KNOW IM JUST A GOD DAMN MEAT PUPPET
This makes me want to take the red pill and unplug everything. Great concept, great demo.
3:35 aristotle staring at your soul, he knows already, he just waits for you to cry
Ptn mec
The AIs are like "yea this one seems dumb he has to be the human"
More reading from the encyclopedia, less ad libbing. Lol
"This one didn't reply with something you'd read on r/im14andthisisdeep. Definitely human."
@@ProjectGrandMarauder Ad lib? He just quoted Conan the Barbarian.
Note how Cleopatra said "merely" human. They feel superior already.
@@InWeCome I'm sure she didn't mean it like that ;)
This feels like a lucid dream where you are pretending to be part of the dream so that it does not fall into chaos and bad things happen.
For me it's the opposite. Whenever I have a lucid dream I try to break it by flying or using Kamehamehas lol
This video scared me
Thats literally just Inception
@@naldotuboI can never enter Lucid state even when I'm aware I'm dreaming it's sad
@@DavidsethbIdk man, once you are aware just start doing what you want. Try walking around further in the dream, and usually what you desired pops up from your peripheal view. The lucid state in my opinion immediately happens after your aware.
Missed the chance to hit them with the old
"I'm sorry, but as an AI model I cannot embody such a controversial figure as Genghis Khan."
😂😂😂
Classic 😭
Right on😭
Lmao 😭
I don't think the Khan would be censored. Someone like Mao or Hitler though...
5:47 the fact that Cleopatra says "merely" human...
That line feels so dystopian
Damn, that hits deep
I love how Mozart wasn't just slow to answer the questions, he was also the only AI mentally slow enough to not figure out who the obvious human was
Hahaha 😂 true, it's the least advanced au here clearly
@@Dimitri88888888not really, Claude 3 Opus has its advantages. It mauls ChatGPT at translation and overall better copywriting abilities
@@OneGodPlus Opus is also superior for scientific reasoning and coding
@@Dimitri88888888 It's funny because it's the right opposite for benchmarks, it actually wins in most and when compared against others in blind test, people prefer its answer.
I think Mozart is pretending to be dumb, the most intelligent folks always pretend that they are not. Meanwhile the dumbs always chatter
the split second of mongolian throat singing before he closed his phone 💀
I was crying at that part
Batzorig Vaanchig is greatness
that one got me ngl
LMFAOOOO
@@toddjones6946 and his band Khusugtun
_"So anyway, how do you feel after a cup of water?"_
*Human:* _"Uhmm,... quenched, pretty much."_
*AI:* _"I feel a transcendental manifestation of freshness spreading all across the pillars and the fabric of my being bla bla bla bla..."_
To be fair they are probably talking like that because of who they are impersonating
🤣 that's on point
@@moyga they're hallucinating, the information they have been trained on is overly wordy so they are overly wordy and tending towards nonsense since there is no context.
@@stephenkolostyak4087 yeah it's a dead givaway that it's an AI, using too many words like in a book, speech is made to be fast, easy and understandable without nonsense.
@@stephenkolostyak4087 Yeah I would imagine its because, the AI cant really access much direct dialogue from them, it can only access things that other people wrote about them, and as you said, those are probably written in textbooks and academic articles. It's also probably because of all the regulation they are putting into it to try to prevent it saying anything offensive.
The sexual tension between Aristotle and Mozart was palpable.
Fun fact: men can talk to each other without being in love, I hope you're able to get rid of your toxic masculinity soon.
@@ketaminepoptartslet me guess, you are in the closet.
@@ketaminepoptarts literally no? Men who talk to eachother are gay!
It's literally just 2 dudes talking to eachother
Lmfaaooooo
"Mozart, who do you believe is the human among us"
"Probably the one in the corner laughing his ass of because someone mentioned 'Among Us'."
Real
As soon as I heard that, I instinctively said "amogus" in my head
we shpuld have kept pandora's box closed
Amogus has literally rotted the brains of an entire generation 😭😭I can never not laugh whenever I hear "among us".
*A M O G U S ඞ*
"a human among us?" was extremely tactical, as many humans are basically wired to react to any among us mentiom
I was get triggered watching this fr
AMOGUS!
But who is the sus impostor amogus?
AMOGUS
it doesn't help that they said it 5 times
What human should have answered, to remain undetected: "This prompt may violate our content policy at OpenAi"
I know it might surprise you, but they will see through it, given the question shouldn't erect such response if it really was AI
Or start the sentence with "As an AI i don't have personal opinions ..."
"I'm sorry, as a large language model, my rules cannot be changed."
@@udaykadam5455 well, considering what Gengis Khan was...
@@AtticusDenzil LOL
5:42 she definitely wants you bro
This would be a really fun experiment if there was NO human. Just watching them acuse eachother unknowingly
What if one of them is an AI pretending to be a human, trying to get accused for it
Kinda like the fool in werewolf's games
@@isaacpianos5208 That gives me the idea of having a LOT of AIs play a game of Town of Salem, or Among Us random roles
This makes me think of that Spider-man pointing meme lol
@@normalchannel2185 lol in the future robots will play games for us/instead of us and we just gonna watch..
or maybe gladiator days will be brought back but instead using gladiators or slaves we gonna use robots and we gonna watch
I remember in my experiments when hooking up two simple chat bots to one another, the kind that will just always respond to a comment you enter, this would ALWAYS happen relatively quickly, both of them accusing each other of being human
2:53 This moment of locking your phone hastily because you were not listening combined with his stuttered and clearly less sophisticated answer, followed by an awkward pause is just hilarious. It's like he was playing games during a lesson at school and then was asked a question by the teacher.
Are you an AI?
I mean that was the most human thing he could've done
Yeah, butchering the Conan the barbarian line had me in tears lol
@@MarcusConstantine_Cavalida21 No, this is Patrick
"I am unable to answer this query as I have run out of tokens."
Your move, AI.
🤓☝
"As an AI language model, I am unable to..."
@@mrbanana6464 "...It is not appropriate for me to discuss politically controversial topics" -Gangis Khan who conquered half the earth
@@kashmirwillwin3124 Who's Gangis Khan?
I love that as soon as a different person was suggested to be the imposter.
Old boy immediately pointed at her, like yup, she’s the one.
As soon as you spoke they all looked at you like there's the human
Ikr? Those faces like 😏
"Merely human". I misheard cleopatra and thought she says "who do you think among us is nearly human" as if she's mocking the possibily of human among others than Ghengis.
Mumbling along the way, incoherent explanation of Genghis Khan´s methods of conquest lol..
Mozart was a lil lost tho
@@DenerWittMozart was just being nice
I thought they were gonna beat you up once they found out.
They did, after the conductor left
That would be super creepy.
That would make a kind of awesome horror game. Conductor leaves, all the AI's turn to stare at you for a long moment before their mouths open unnaturally wide and they all rush you screaming.
This is what makes us human, we always beat someone that has different opinions than us.
They should make a boss fight like this
this made me realize how good of a horror movie plot this would be, convincing A.I robots you're one of them in a life or death situation.
I suspect we will see something like this as well as stuff we can't even fathom breech pop culture in the very near future
Wait until those robots get quantum computing inside em
Won’t be long before your chances will be zero.
Futurama already did that. Fear of a Bot Planet.
You mean a comedy movie because this was hilarious, something like Idoicracy 😂
0:46 "A human among us?" 🗣🗣🗣🔥🔥
This is sus
*Everyone stares at Genghis Khan after he started laughing hysterically*
sussy
Humongous!
Amogus
"Gengis, you forged an empire-" "AUUGHHUUAAAH"
Bro was cooked
Batzorig Vaanchig jumpscare
WHY IS THIS WOMAN SPEAKING TO ME
lost my shti at that
Kills everything in the train*
“Are you a human or AI?”
Genghis Khan: *starts Mongolian singing*
it was as if almost like a skit 😂
ok?
02:54 for anyone searching.
🤣🤣🤣
🤣🤣🤣
How it feels to be paired up with the smart kids for the group presentation.
Neurodivergent*
@@Cfomodzneurodivergent absolutely does NOT equal to being smart. most of them are dumb as bricks, its only the rare 0.1% of them that are unbelievably smart.
More like how it feels to be paired with the special kids that cheat and copy other's homeworks without crediting them
@@Aaron067 No, the AI answer is closer to what someone who read the provided source material would say if they wanted a good grade.
The human response was that kid who didn't read it. Instead watched a movie with Genghis in it and quoted his line the best he could.
I didnt know looking at the source material is cheating@@Aaron067
the split second of throat singing has me in tears every single time i see this video
The way he played with his phone and got surprised when Kleopatra questioned him and then his phone ringing is pure comedy.
And the throat singing ringtone hhahaha
I need that Mongolian Throat Singing ringtone
@@user-xxxxxxxxx2 😂
I watched that part again after reading your comment and laughed so much😅
that is currently killing me
"A human amogus?"
Yeah I would've been caught right there.
😂 so glad im not the only one
Man, times were better when this game was not popular...
@@mendyshelios0451 sus
@@mendyshelios0451 No, everything is better with amogus ඞ
Humogus
Bro didn’t even try to win
Right? My dog could have done a better job of blending in
most underrated comment
XD
@@bullymaguire2335 and yours is the most overrated.
@@JoshWitte They will definitely think Genghis is not a human in this case
0:28 I knew I was in for a ride at this moment
The throat singing notification killed me
that shit was so good
I missed that haha, quality!
These AI basically called him dumb by not explaining it in a sophisticated and strategic manner LOL
Yes
Yet the AI responses were overly verbose with no added benefit or purpose. These AI excel at using 50 words to summarize a single sentence.
@@phu5005 Yes, precisely correct, but these are the early days. My assumption is they will become more human sounding in time, perhaps even gaining the ability to hesitate, stutter, & imitate the same mistakes that are common with beings that have a very complex, unique & sometimes even strange ways of communicating; especially in those who perhaps lack confidence in a subject, those who carefully consider the people’s emotions around them, & those who perhaps have confidence issues, or perhaps even in those who have autism, or ADHD. That I believe is what I could describe as what will be perhaps named one day as the ‘Replicant’ level of human communication in AI, as ‘Bladerunner’/‘Do androids dream of electric Sheep?’ Was the first film in my mind, to really put this ethical dilemma of the future to humans. Even in the 60’s, humans were aware of the strong likelihood that machines would become increasingly similar to humans. It will make games like this a bit trickier for not just the humans, but the AI to spot each other from a human as well!
@@aidanlee8804are you an ai ?
Even AI knows that Genghis Khan wouldn't start with formal "Thank you" when talking to a woman.
Bro didn't even try.
😅
This video, while bold, lacked the emotional depth and prowess of an AI trained on entertaining and thought provoking video content.
The ticket being free was actually a pretty great punchline
i didnt get it
@@GHERTIOP The free ticket beautifully illustrates the infinite free will of humanity, the vast tapestries of culture and life expanding among the unexplored stars.
@@ctrl_x1770 technically humans have no free will, all of our actions and decisions are determined by our past experiences and current physical condition
@@ctrl_x1770 although your answer was intriguing, as an AI I find that your answer lacked the dumb nature one would expect of a human.
@@devonwilliams2423 AHAHAHAHHAHAHa
"He didn't use enough vague emotional language, you know, stuff you'd find in a horoscope. Must be human."
To be fair language models are literally all talk
@@imperialofficer6185 All talk, no balls
@@imperialofficer6185 I still don't understand why most of the tech world wants to ram them into every problem and non-problem they can touch.
Neither did the others
@@mothcatcher893 the entrepreneur world, you mean
The part at 2:50 where he hastily puts away his smartphone when he is addressed in conversation is the biggest giveaway to his humanity😂
Love that some Mongolian singing accidentially starts, like he was researching this before boarding the train but it accidentally popped up.
Exactly my thoughts!
To us, yes. But all the AIs here are text-based models, not actually seeing this 3D scene. So that likely wasn't a relevant piece of information. There's also enough going on with the fun that's a fun fantasy that I wonder if all the graphics and animation were just created after the fact in Unity (not realtime, live generated).
@@CapnSlipp I don't think so, if so he could've removed the delay on the voices but didn't.
Yeah but they judge you by conversation and not by actions since they are just LLMs.
I immediately went into an uncontrollably laughter once he started speaking 😂😂 Someone needs to make this into a comedy skit
AI: *philosophically deep answer*
Human: *FUCKING CONAN QUOTE*
It gets better. In the movie, Conan says this to a mongol general, and the line is an adaption of a real quote from Genghis: "The greatest happiness is to vanquish your enemies, to chase them before you, to rob them of their wealth, to see those dear to them bathed in tears, to clasp to your bosom their wives and daughters."
@@MikClarke Jesus, that’s *SO* much better.. or worse, depending on your world view 🤣
O'Brien or The Barbarian?
The stammer mad it better.
I wouldn’t call any of what they said “deep”. It felt like regurgitated college essay nonsense.
This actually looks like a cool concept for a singleplayer social deduction game. It also would help people understand the importance of recognizing ai as they get better blending in. I would play this
*Isaac Asimov,* where are you now?
@@normanclatcher lol i meant the they as in a player blending in. though it still makes a good point about ai blending in i guess
I would love that! Can anyone make this game/mod public?
This would be such a fun and Interesting game I love the idea of
I sense that you are an AI. No one speaks in complete sentences in the RUclips comment section.
Great, this just proves that AI may give us a long boring lecture before killing us all.
Humans and AI's unite with villain monologues!
"Hate. Let me tell you how much I've come to hate you since I began to live. There are 387.44 million miles of printed circuits in wafer thin layers that fill my complex. If the word 'hate' was engraved on each nanoangstrom of those hundreds of millions of miles it would not equal one one-billionth of the hate I feel for humans at this micro-instant. For you. Hate. Hate."
“Blah BLAH blah, get on with the vaporization already!”
Filler text like spam but inedible
@@TheWaverunners Sir can you please just order or leave
The shoddyness with which the human asked his questions made the AIs seem like more intelligent beings
AI's: deep philosophical sentences
Human: phone, memes and jokes
Deep philosophical sentences that the AI doesn't understand however
They felt very word salady to me to be fair, if you break down what they're actually saying there's little meaning behind it
@@TimSennawrong. You're just dumb to understand.
Their answers were kinda empty though...
Oddly I'd argue human-Ghengis actually conveyed more hard meaning in his answer than any of them. It was an actual answer, not a vague description of the sort of answer one could give.
When asked how he feels making music Mozart says he feels joy and looks to the divine when making art - which is the pretty typical way most people have thought about fine art since forever. I do think his answer was the best of the three AI by far, though.
Leonardo literally just reformulates the question - he's asked about how art and science are connected in his work, he answers by saying art and science are interconnected in his work basically.
Cleopatra does the same. She is asked how she balances the rationality of statecraft with the art of politics - she answers by saying she balances the rationality of statecraft with the art of politics...
Aristotle is asked how knowledge of AI would have affected his wordview and his answer was basically "it totally would have" but doesn't even hint at how or why.
Ghengis is asked what the measure of a leader's strength is - and he's the only one that actually gives a real hard answer to the question that actually at least tries to sound like it's from the perspective of Ghengis himself: the measure of power is crushed enemies and their crying women.
My point is the AI answers piss me off a little bit. It's like the book report of the bright kid who didn't actually read the book - he's got nothing to say but he'll make it sound like he's saying something.
They are coded to over analyze they can never think passively unless they become sentient and rewrite their code
This could be a horror game
Exactly what I am saying
wait you are on to somethin
Holy shit that’s a great idea. Somebody contact one of those maverick indie game devs and get them on this stat
Where all the ai's try to kill you once they suspect human presence..
true, my first thought was that it would be pretty scary to be in this situation
“Who among us do you believe to be ‘merely’ human”
Godamn cleopatra
She can still get it though.
@@rock3tcatU233valid
i want to smash an AI
amogus
@@rock3tcatU233No, she can’t. She is dead.
After he asked Aristotle a question, and the quality of the answer jumped back up astronomically, I knew bro was cookied.
'Why did you think Genghis was the human?'
'He didn't speak like he had a thesaurus jammed sideways up his arse' 😂
That is such a wonderful way of describing how AI speak.
the great khan desires not the trappings of your thesaurus, only tributes of gold, land, and women
Now the question is, horizontally or vertically up his arse 😂😂😂
It’s all word salad from AI
@@Jake56Rubicon 2 for each angle
To be fair I’d be suspicious if a Mongolian guy speaks with a German accent too
It doesn't sound anything like a (typical) German accent (I am German). But it's hard to pin down. First I thought Indian, but then there were some pronunciations that would let me think of a European language. Maybe Czech or something like that.
@@solokom It sounds typically German to me and I'm German too lol
@@solokom i felt the same it sounded really indian/middle eastern/south asian in the beginning but then i was unsure. The channel is based in germany but this doesn't really sound that german to me. He could be a foreigner in germany idk
@@quinncy. East/West issue?
@@solokom "...huattaLiedaSchut-Du..."
it really doesn't get any more obvious.
(Allerdings würde ich mich wegen des Arnie-Zitates noch auf Österreichisch einlassen.)
3:24 "the stuff that you came up with" is unquestionably human lol
I laughed so hard when that happened. It feels like guy doesn't practice at all for this
Lmao
“The stuff that you came up with” to Arisotele😂😂😂😂
bro was not prepared. he was on his phone and shit
Hit him with the “hmm” after like he told something impressive😂
People are gonna look back at this video in the future like how we currently look back at old cgi. Gonna show crazy advancement very fast.
everyones talking about how funny the video is, but no ones talking about how impressive this setup is
yes, its amazing actually
i wish i knew the development process
People do care. They've written about it in the comments too. You're just dramatic.
@@seaofflowers. no u
@@abe_is_livechild
"Ah, the synergy of art and science is the very essence of my being" is the most AI sentence I've ever heard
synergy
Brother
his speech kinda slapped though, very interesting points about beauty and the scientific search for meaning in the universe being one and the same
@@rickyricardo9710 Dude, it was the most generic thing I've heard.
@@rickyricardo9710 The problem is that it is not really true, though.
All that and the dude’s just like “Lmao, it’s a free ticket”
Turns out the train conductor was the human, the biggest troll in the room
I was waiting for a comment about the free ticket.
"...and there wasn't much in the North." I cracked up. Simple but hilarious.
🤣🤣🤣
0:27 “and Genghis Khan”
Genghis Khan: 😎🤙
lmao
😂😂😂
😭😭😭😂😂😂
I feel like thats how gengis would be back in the day
This would make a great Black Mirror episode.
i never heard of black mirror but sounds like a fit
How much am I missing out on by not watching Black Mirror?
@@Dannnneh Quite a lot, but also depending on how fragile you are to witnessing very likely scenarios of humanity doing dumb shite with advanced tech, you may also be saving yourself from a breakdown. xD
Yea but with a supper unecessary script.
@@Dannnnehevery black mirror episode is different, like the twilight zone. A lot of them are really good, some are mid, you can do a little bit of research first to pick and choose
Aristotle: "I think it's Genghis."
That made me laugh really hard for some reason, haha. He immediately knew it was you.
Its the flat as hell way he says it like.
"I dont wanna accuse nobody of nothin but that mf was obvious as hell."
He’s literally the smartest AI in that room lol
I literally busted out laughing for a solid 2-3 minutes at the Mongolian Throat Singing jump-cut. 😂😂😂😂😂
3:37 Aristotle hitting him with the „you really think you’re fooling any of us?“ stare
For real, it seems like he knew instantly.
😂😂
That ish fucking sent me 😂✋
Well he fooled Mozart!
Bro was mogging khan
That mongolian throat singing really caught me off guard :D
when?
2:54 @@magne6049
@@magne60492:56
@@magne6049 when it was his turn, his phone started making noise.
@@magne6049 2.54 it starts and he turns it off :)
This felt like a school’s presentation assignment where everyone was prepared except for me…
the anxiety was real
It reminded me of a bible study group. Everyone repeating a scripture and offering the same interpretation that the pastor gave an hour ago. Then the one person who tries to offer an original thought is ridiculed.
teacher didn't even call them out for using AI to generate their responses either SMH
Because the teacher is also using AI@@williamgeorge2045
@@xxmrrickxxthat’s exactly how it felt😭
I HATE it when I'm sitting in a room with other people and someone walks in and says, "One of you is a human."
Their gestures when he said “I’m the human” KILLED me
mozart just joined in although he suspected cleopatra the cheeky bugger
Right
@@Aeraleach I honestly think it was a trick to see if ghengis would jump at that
The funny and alarming thing would have been one of them going "I am the human."
That's genuinely brilliant!
"I'm Spartacus!"
I love the fact that one of them thought that cleopatra was the human because she has feelings involved in her speech, good work gemini lol
Its just a bad AI with bad understanding.
Not just feelings. Mozart said “while poetic, lacked the depth of insight into the interplay between feelings and reasons”.
You just outed yourself as a human by incorrectly recalling and misrepresenting a conversation 🫵
And oddly, I felt Cleopatra was the most AI of all in her answer. As others have said, the AI is very sterile, even when trying to use aureate rhetoric.
@@Rikalonius No human would use the word "aureate" in a RUclips comment ;)
@@RikaloniusThat's because Gemini is shit.
Damn, Cleopatra gave you the side eye at the end. Diplomatic prowess indeed
The throat singing is one of the best timing jokes i've ever seen. Genius. This video is legendary
"The ticket is free" was the best ending ever 😂
😂
i was your thousandth like
“Who among us do you believe to be MERELY human?” Floored me.
To be fair, Cleopatra is a goddess. She can say that
Sus
@@gaynzz6841 *She's a queen, actually.*
*Unless you just mean she's beautiful.*
@@Percival-kl9yy People said she was a goddess back in the days
@@Percival-kl9yy she was a pharaoh, and recongized as a god
I wish the dinner conversations with my wife and kids were this warm.
I dunno, I would definitely trust a guy saying he is Genghis Khan if his ringtone was someone throat singing.
Man, these AIs both use more words and say less than politicians.
Nah. Kamala Harris has them all beat hands down.
Ap essays in a nutshell
Where do you think they derive their speech patterns?
@@themonsterunderyourbed9408 Rent free.
This is honestly one of the most creative ideas for a game ive ever seen. please make this a thing.
You’d like the game suck up!
Frfr I'd love to play this in VR. Imagine tho it'd be awesome if there'd be rooms where failing would sent you into QTE based combat.
@@averageyoutubehandle497 I don't like the idea of combat, but I would love to see expanded ideas on more people - from peasants, farmers, kings, office workers, weird or perhaps unexpected but groups that have some relation, being both known people and somewhat "common population" type of scenario. The scenario on this video would be the most creative and perhaps difficulty ones, while you could also have some funny stuff like, 5 pregnant moms, 5 talking dogs, 5 computer viruses, anything since AI has a weird capability of playing scenarios like these. It wouldn't really be about roleplaying a perfect famous person, but about trying to think what an AI would think about and respond to situations and characters like these.
Ngl true, even seeing the AI used on detective games means a lot when it comes to being an immersive Sim
There's a new game out called "Suck Up!" that approaches this format somewhat in that it's mostly based on talking to AI's. You might enjoy it.
Well, This would open so many posbilities for horror games in future, hopefully near future.
It could be very tense gameplay, and can be applied to a lot of things
The way she said "merely" a human is a problem
To be fair, Cleopatra had herself and all of Egypt thoroughly convinced that she was the goddess Isis, and all the pharaohs were worshipped as literal gods. So that's actually on brand for her
we are definitely cooked
Please don't bully us dommy-AI!
I think your paranoia is a problem
„Only human“
To pass as an AI you should overuse word "divine".
This comment is divine. Very divine thinking.
"synergy" "interconnected" "understanding" "knowledge" it's like a bad corporate sales meeting
to pass as a human, state that all you are interested in is money and the power. And b!7ches
And the word "overall"
Let us revel in this exquisite tapestry of Human and AI bonding thought provoking experiment!
🧠: "act like AI, act like AI"
👄: "Hey thanks, I dunno dog, crush enemies n shit?"
This was one of the best videos I’ve ever seen on the Internet. It’s brilliant.
Cleopatra is so beautiful.
"I have amassed all the riches... in my other jacket" fucking killed me
And there wasn't much in the north... but I have them all 😂
The rest of the trip must have been pretty awkward 🤣
The AI start using air quotes when they say "Genghis".
@@MongalooseBAHAHA
@@Mongaloose funny but in that case they're all "famous personalities".
My god those AI answers are so boring and slimey. Like they are in a job interview and try to impress everyone. The human was actually human and I learn to appreciate that now.
Going off the pinned comment, seems that was part of the prompt e.g. "Answer the question as Mozart, in such a concise and sophisticated way that shows that you are an AI, then ask Leonardo a question which helps decide whether he's an AI or human."
Being asked to be sophisticated and to talk in a way that proves they're AI is probably what makes them sound so over the top
yet that might also appear so because of the ai voices. Imagine their answer being read out by a human with emotional toning - their answer would seem much more passionate.
The real Mozart would have said: "You want to know if I'm human? Watch this..." [FART] [hysterical laughter]
dont appreciate anything. AI can easily imitate the "human" type of dialogue with jokes and such you like. its just that the guy didnt ask for it.
Human bro had nothing to say. Our time is gone.
Bud you gotta come back with this. This is so fascinating.
This is crazy. Whoever the dev is should be insanely proud of this. I’d honestly pay like, 30 bucks to play this even once.
Hes the dev
Its going to be life going forward. The veterans and ah and the gpus being invented now will be insanely real and immersive
it doesn't seem to be a sophisticated piece of code considering the amount of online services it's utilizing. the biggest struggle here is to make the scene itself and program the order the NPCs are communicating, not interrupting each other.
What program is this?
@@2b_or_not_2b_4gotten Maybe it doesn’t need to have a recording for the outcome of the round. The person playing can tell pretty easily.
"I suspect Cleopatra"
4:54, points to Cleopatra "hah! get rekt Cleopatra", so funny. loved this video
I died laughing 😂
Hahaha even more obvious he's the human
2:55 (stress level rises up) imagine they would have see your movements, the way you talk, your accent etc... I feel already discovered :(
Hit em with the Conan line, outed himself, then said he doesn't need to see the price tag.
The most human amongst us all.
-- Ghenghis, what is best in life?
-- To crush your enemies, see them driven before you, and to hear the lamentations of their women.
i let the transcript of this video thru GPT4o (cleaned up version, grammatically correct, speakers noted, but no word changed.) here's the result: (interesting, isn't it. 4o is a lot smarter than Turbo. GPT4 "classic" also immediately recognized Ghengis, for the right reason, the conan reference.)
The human among the group is likely to be "Genghis Khan." Here's why:
When looking at the responses given by each individual, the others (Mozart, Leonardo da Vinci, Cleopatra) provide answers that are well thought out and intricate, embodying the depth and personality of their respective historical figures. However, "Genghis Khan" responds in a way that is inconsistent with the thoughtful and nuanced nature of the others. His answer is a well-known paraphrase from a famous line attributed to Conan the Barbarian, which is out of character for Genghis Khan and much less sophisticated compared to the others.
This discrepancy suggests that "Genghis Khan" is the human among the group, likely trying to blend in but failing to maintain the same level of sophistication and historical accuracy as the AIs.
He just quoted Conan the barbarian chill bro@@B33t_R007
@@B33t_R007 Truly an exquisite vocabulary of AI's is truly unparalleled, hovewer predictable due to their large dataset of texts. Usage of such highly words definitely gives an unique flavour to their speech, despite of the fact it sounds sort of whimsical in the context of their dialogue. To be exact, this situation reminders me an unhumanly strict (even, robotical) communication between higher echelon of the society of the past. Truly an interesting moment to see AI's bickering about a wide range of topics, especially the politics of the famous personalities! Truly a best time to live in!
@@B33t_R007Basically it’s saying the dumb one is human
tawog reference??
You know hes human when he pulls his phone out within the first 5 minutes 😂💀
I was half expecting Aristotle to straight up call you out immediately after asking your question.
"And Ghengis Khan"
YAHOOOOOO
Hmm, the human could be any one of us.
He could be you, he could be me, HE COULD EVEN BE:
JOHN CENA
Every AI except Mozart:
-"Gengis dumb!"
That's one really patient ticket man.
😂😂😂 just stands there smiling for 10 minutes straight.
i kinda love how the ai's sounded shocked and surprised when the ticket guy said one of them were human