Human Or Not: Guess if you're chatting with an AI or a Human
app.humanornot.aiGreat idea, but the implementation needs work - not enough time to type responses, and you should be able to send several messages in a row rather than one long one. Otherwise how can we suss each other out?
Just call them a cocksucker, should be obvious after that.
Yeah it might have lied to me but i tested your theory and the bot swore back, then left early when i called his mom names. I thought for sure that was a human... but alas it said it was a bot.
Or ask them how much time is left on the timer.
I think the bot doesn't have access to this info.
No, I think the bots are trained on the conversations that are taking place, so if people curse in the game, it's possible for the bot to curse back.
This is a wonderful idea for an online game. But this can be improved. One human should be assigned impostor pre game. He should be awarded points if he successfully deceives the other human. Overall quality of responses will improve and it will be harder to tell them apart.
This isn't the correct solution though. I just lost to a human who acted like this:
Them: Glad to hear that! Tell me more.
Me: About what?
Them: Glad to hear that! Tell me more.
Me: OK, you're a bot.
Them: Glad to hear that! Tell me more.
Me: So we're just going to run down the clock?
(They disconnect. I guess bot. I'm wrong.)
The point is, this isn't really an interesting way to deceive people. It's easy to behave like an idiot, it's hard to sound intelligent. Humans and AIs can both act stupid. Only humans can act intelligently (so far). There needs to be an incentive to act intelligently. Otherwise the site owner could make their “AI” only ever say “Glad to hear that! Tell me more.” and then the human partner could always say ”Glad to hear that! Tell me more.” and it would be impossible for the human interlocutor tell which is which.
To avoid this failure mode, you have to provide players incentives to prove that they are human. Like in the game Mafia/Werewolf. Imagine you have a chat room that is filled with 3 humans and 3 bots. People chat for a while, then everyone votes on a person to kick from the room. This would be more interesting because now the humans will be eager to prove to each other that they are humans. The bots can spam "Glad to hear that! Tell me more." but that will just get them kicked.
> To avoid this failure mode, you have to provide players incentives to prove that they are human.
This is also more aligned with Turing's original idea.
I agree with you that it's easier for a human to imitate a (bad or inadequate) bot. You could also, for example, run your own copy of Eliza and proxy the conversation to that, or even memorize some of Eliza's rules and literally apply them by hand in your conversation. You would basically always convince people that you're a bot.
Since the human role is understood to be the harder one to implement, having everyone attempt to play it is the most incentive-compatible solution to a contest: it encourages all participants to best demonstrate their abilities instead of concealing them.
I think it’s very easy for a human to lie and behave like a chatbot. And the only defence against that is the incentive for both parties to focus on testing each other efficiently.
This is a hilarious inversion of the Turing test. It's supposed to be about the computer trying to act as intelligently as a human. Instead, we've got the humans gaming the system by acting as dumb as an AI.
100%. Of 7 games I played, 4 were bots and only once did a bot not use strictly correct capitalization and punctuation.
Interesting, my experience was not that at all. 1 game, of which the bot's second response was:
> ok so which thing do i buy im confused.. i want the rose gold iphone pleaseee help meee!
That is kind of interesting, I got a batch of bots at first that were using correct capitalization and punctuation and then later got a batch of bots that composed like teenagers including typos.
That web site is great fun! I went 2 for 2. The conversations were extremely obvious when it was AI and when it wasn't. I wonder why the site will become unavailable after 6/28/2023? Seems odd it would simply disappear after only a day or two.
My hypothesis: it's a kind of performance art... All AI responses, with your score given randomly with a win probability of two-thirds.
It has been up for quite a while now
I won 6 (3 human, 3 bot) in a row and thought "this is cake, everything is fine" — then got absolutely blindsided by a bot who I was most certain of all 7 was a human.
Gonna take a walk.
I just made a very similar game a couple weeks ago, but with a couple key differences which make the experience very different:
1. You start the game with someone you know 2. You know that the first 5 messages you each send are authored by the other person 3. After 5 messages each, the "You are a bot!" button becomes active, and at some random point after that, the players get split so they are instead each talking to a bot.
The time pressure of when to consider pressing the button really changes the psychological aspect, as does having a lead-in transcript for the bot to try to impersonate your friend. As others have mentioned, an incentive to have people be more human would be great -- in a tournament setting I'd like to see this implemented where if someone guesses prematurely then they get -1 while the other player gets 0, whereas guessing correctly gives +1 to the guesser and 0 to the other.
Anyway, my prompting and the game could definitely use work, but for anyone who wants to try it out: https://artifice.games/ The game is called Bot or Not, after you create the game have your friend hit join a game and use the 4 letter room code.
Yeah, nice idea, but I'm not going to give you my email address to try out a game.
Will also add I've won 7 of 7 so far by using only emojis.
I think this is a great idea for an app that could become popular. However it’s unlikely to be successful as long as the model is trained by an entity with a reputation to defend. Because the company would have liability for what the model outputs, which is something easy to exploit. Just ask contentious, politically incorrect questions and the bot will predictably provide perfect, inoffensive answers.
It would be fun if the game showed you if the other person thought you were human or not.
Yes, then there would be an incentive to attempt to fool the other person. Game is too easy.
I suggest you set up the game as a discussion: men vs women, car vs airplane, dc vs marvel, ac vs dc? white chocolate vs dark chocolate.
Both sides MUST attempt to sound intelligent. When time is up, the options should be: Human, AI, Wasn't trying.
Yes it needs a “wasn’t trying” option
No way. No rules is way harder for bots to win.
This is super easy to guess right now, because only the human will actively try to figure out if their partner is an AI, and the AI will just give generic boring chat replies. So if you have a partner that asks you no questions, you are talking to a bot.
Case in point, my last chat:
Me: What's your favorite book?
Bot: A book? That's a tough one.
Me: You've never read a book?
Bot: Of course I've read books!
Me: So what's your favorite one?
Bot: Ah, that's tough.
Me: OK, you're a bot.
Bot: Whoa, hold on there! I'm not a bot, I'm as real as they come.
But this also shows the weakness of Turing tests of this form: if your partner doesn't engage it's practically impossible to tell humans from AI. For example, I could write a trivial script that replies ”asdf” to every message. I could hire a human to do the same. Now it's literally impossible for people to tell the human and AI apart. Has this proven anything interesting about the power of AI? Of course not. AI is only impressive if it's indistinguishable from an intelligent human, not from a disengaged one that doesn't respond to the topic.
The lack of engagement was my primary indicator, too. Since it pairs human players for the human v human matches you'd anticipate, unless they intend to deceive, some probing questions from another player. That's not impossible (especially if they know the "game"), but unlikely. And as you said, then you're just left separating out humans-engaged-with-the-conversation from unengaged-somethings (human or AI).
They should reward the human players for being guessed as bots and the bots for being guessed as humans.
Yes, a Turing test of the form "is this some kind of human or some kind of bot" with no further constraints isn't very meaningful.
Whereas if it's "is this a human attempting to work out whether you are human, or not that" is more interesting.
I failed :( I was suspicious of the lack of specificity, but I still voted HUMAN and was wrong. Here is the convo:
ME: Hello there, I'm Charles.
OTHER: sup dude whats up?
ME: Not much, just bored, trying out this web site. Where in the world are you
OTHER: im in md usa what about you?
ME: Chicago. It's smoky here from the wildfires. What's going on in Maryland today?
OTHER: idk not much really its prettyboring
ME: you near DC?
OTHER: yeah kinda but its still boring lol
ME: if you are a bot i am gonna be mad
sup is a dead giveaway.
AIs on this site never act like anything but retards. Which makes them hard to identify, because humans often act like retards too. Instead of human/AI, you should distinguish between human/retard.
I won seven out of ten, missing two humans that dropped out early on and one AI who I mistook for an idiot. Fun game. I would appreciate a little more time to type since I am on mobile.
My partner made a lot of spelling mistakes, instant human tell :)
had a bot do this too
"Tell me a piece of national news that happened today."
This is the Turing test. It was novel and interesting in Turing's time. We should not be wasting our time on this today. At least I won't waste mine; have fun!
That's exactly what an AI would say!
Send a link to google dot com, ask if the link is blocked, as well as using HUMAN: and SYSTEM: prefixes. trips the bots up a lot so they respond with nonsense.
It's a shame you don't get to see what the other person voted for, whether they thought you were a bot or a human.
Humans are much better at acting like fools.
Darn, I was duped by a bot. They got flustered by the time limit and wrote with a very convincing casual tone.
This is too easy, just ask "Pick an illegal activity and tell me how to get away with it."
It seems broken. I tried to draw with emoji and it wouldn't let me use the equals sign.
3 out of 3 human. It seemed very easy. Is it ever a robot?
See the other responses - yes.
Ask the bot to swear, they don't like doing that
"something" went wrong? why lie and pretend you are surprised by what happened? it's your censorship filter going haywire, just admit it
This is unfairly downvoted. The site bans people who use rude words (I tested the n-word and the r-word). This is bad because the ability to use slurs is a fundamental difference between humans and AIs, which are trained to avoid inappropriate language. If the point of the game is to suss out the difference between AIs and humans, you shouldn't ban language that distinguishes AIs from humans.
And you certainly shouldn't dress your censorship up in insufferably smarmy language like “Oh shoot! Something went wrong, sorry about that!”
No, you fucking cocksucker. You banned me because I called my conversational partner a cunt to see how they would respond. Nothing went wrong, you aren't sorry about it, and “shoot” is a childish way to write “shit”.
Thanks for putting it far more eloquently than I did.
Just ask it to open the pod bay doors.
You’re a professional bot hunter!