At least you got someone to talk to. I got "no other humans online" and told to come back in 59 minutes and 39 seconds...
Anyone know the significance of the time? Or is it just trying to be more effective than saying an hour? (In the same vein as parking lots that have speed limits of 4 mph rather than 5 mph so that motorists are more likely to actually watch their speed because it's different)
I met a human. I wrote "Who am I" and then "Who are you" and then s/he said "What is life" and I said "Cats". This made him/her think I was a robot :- )
+2 to me
It would be fun to see a pic of the other person, and to chat for 90 seconds instead of just 30. And maybe continue chatting for 90 seconds afterwards.
My partner didn't reply. From that I guessed correctly that they were a human, but (for a 30 second conversation on an interface your users will be using for the first time) just saying nothing would be an effective low-effort way to implement the chat bot.
Would be nice to increase the time to a minute, I tried a few times but only got two lines back and forth before having to guess. It was always a human in my tests though so perhaps the bot would respond quicker?
Love the idea though! Hope you can share the results and analysis with us when completed
I gave up after a couple of times, 30 seconds is too little time for a conversation. On average, there weren’t more than 3–4 messages exchanged in my chats. If there had been a “I’m not sure“ button, I always would have clicked that, since I wasn’t able to collect enough evidence.
The scoring mechanism, where you lose a point if the opponent correctly guesses that you are human, makes me suspect that is actually a Prisoner's Dilemma simulation disguised as a Turing Test.
The scoring is wrong for a Turing test. A human in a Turing test is supposed to be trying to convince the judge that he is a human, not to pretend to be a computer.
I think something more fishy is going on. Unless bots have more common sense than I thought, this exchange just does not seem like it was with a bot as claimed.
Me: If you push your finger into a cake will the cake move relative to the table it is on?
Stranger: Depends on the amount of friction. For almost any normal table, the cake won’t move.
Me: Thanks!
Stranger: The bots they made are so weird
You predicted: human
Correct answer: robot (-1 points
Correctly guess who you're talking to: 1 point
Convince a human they're talking to a robot: 2 points
You guess wrong: -1 point
Stranger guesses correctly: -1 point
to...
Correctly guess who you're talking to: 1 point
Convince a stranger they're talking to a human: 2 points
You guess wrong: -1 point
Stranger guesses that you're a robot: -1 point
and the robots should also guess and try to optimize for that score. That changes it from a bit of a prisoners' dilemma to everybody trying to act like a human.
is it gaming the turing test to the point of breaching the spirit of the test by having the robot be the worst version of humanity as conveyed on the internet?
in other words: is the turing test meant to hypothetically carry over into non-digital media, or should we only expect it to be a useful measurement when it comes to purely digital interactions?
This is terrible, I was told that the person on the other side will be attempting to impersonate a robot. (This is the scoring.) And that I myself am supposed to impersonate a robot.
So I wrote texts in advance and then copy/pasted the most relevant one, ignoring what the other person said. (To look like I'm a robot.) Some of them (like in response to "how are you") that I wrote were pretty reasonable, other responses by me kind of non-sequitur.
Meanwhile, the other person acted JUST like a robot. So I picked human, since I thought they were impersonating a robot well, as requested. Not being a poorly programmed robot. (As shown.)
The game scoring needs to be updated.
By the way this is my strategy if the incentives were reasonable: I would teach the other person literally anything that I just came up with, and see if they can learn it. Robots just can't do that.
For example I might say (but I would come up with something different each time). "Okay, first I'll teach you something new that I came up with (to prove you're human to me) then you teach me something new you came up with (for me to prove I'm human to you). Absolutely anything new counts. Okay, my new thing is the game of Pirate, I just came up with it [this will be different each time.] I'll say an activity, and you tell me why pirates hate it. Doesn't matter if it's reasonable or not. Ready?"
"Yes".
"Okay, filing taxes."
"Uh ... pirates hate it because... they don't like laws? Or the government"
"Okay good now you".
"Contradict me."
"Okay."
"This game sucks."
"No it doesn't, it's great!"
"Okay we're both human haha."
"Yeah totally."
Now granted this will only work with pretty creative people who can invent a totally new game on the spot. And if any two people ever invent the same new game it might have a false positive. But on the whole I have zero doubt that it works.
I tried it with OK Google. Couldn't teach her anything.
>My strategy works really well - I start telling a role-play themed joke and if they play along they're human. This works great because it's based on common sense, entertains humans, and is a complex social performance that won't ever be the same.
But then deleted their comment. I think it's a great strategy but under the link we're discussing, why does the other person play along if they're trying to convince you they're a robot? If they play along the jig is up.
I guess maybe they meant they do that on something like Tinder (which has a lot of spambots in some geographies) rather than in this actual game.
When you start playing you get assigned a percentage chance of matching with a robot, so some players will get matched to other humans 80% of the time for example
when you start playing you get assigned a percentage chance of matching with a robot, so some players will get matched to other humans 80% of the time for example.
Time: 0
Me: In Spain, where does the rain stay?
Stranger: I dont know the awnser to this question.
Me: That's ok, it's a hard question. Do you like spain?
Stranger: The humans there speak no english but since i can speak any language it does not matter to me.
Stranger: The weather is to hot for my fans.
You predicted: human
Correct answer: robot (-1 points)
Stranger predicted: nothing
Stranger: huh
Stranger: whatis this
Me: Good morning. How is the weather there?
Me: Hello?
Me: Anyone there?
You predicted: robot
Correct answer: robot (1 point)
That's the problem. Since humans are incentivized to sound like bots, bots are (presumably) incentivized to sound like humans trying to sound like bots. This doesn't lead to a convincing chatbot.
Me: alright dude. we gonna kobeyashi maru this
Me: did you come from hn?
Stranger: Hello
Me: site that linked you here
Me: which is it?
Stranger: I'm a fake robot.
Me: Indeed you are
63 comments
[ 4.5 ms ] story [ 131 ms ] threadThey put "fg", then "ffg", then endless, endless carriage returns.
This needs some filtering - currently useless.
Tried again - we got a total of 4 lines, 2 each, and the 30 seconds was over.
Cute idea, completely unengaging for me, I won't go back.
Anyone know the significance of the time? Or is it just trying to be more effective than saying an hour? (In the same vein as parking lots that have speed limits of 4 mph rather than 5 mph so that motorists are more likely to actually watch their speed because it's different)
It would be fun to see a pic of the other person, and to chat for 90 seconds instead of just 30. And maybe continue chatting for 90 seconds afterwards.
Love the idea though! Hope you can share the results and analysis with us when completed
Not exactly:
• Me: So, what do you think about this game? • Me: Hello? • Stranger: It's my first time playing • Me: No • Stranger: Yes
• You predicted: human • Correct answer: robot (-1 points) • Stranger predicted: nothing
Me: If you push your finger into a cake will the cake move relative to the table it is on?
Stranger: Depends on the amount of friction. For almost any normal table, the cake won’t move.
Me: Thanks!
Stranger: The bots they made are so weird
You predicted: human Correct answer: robot (-1 points
Me: If you push your finger into a cake will the cake move relative to the table it is on?
Stranger: Cake will table
I was totally sure that this was some troll, so I was trolling back...
You predicted: human Correct answer: robot
The chatbot trained on this dataset will be so much useful :D
Me: Which of the following is not like the others: dog, cat, parrot, elephant, iPhone? Stranger: hi icm japanese Stranger: iphone
Me: You have to be human.
Stranger: you type too fast it's impossible
Stranger: r u robotm Stranger: ?
You predicted: human
Correct answer: robot (-1 points) Stranger predicted: nothing
Me: What is the third word of this sentence?
Stranger: the
Stranger: nice one
Stranger: you're the first one to use meta to check for bots
Stranger: I always use
Stranger: How many letters in the next sentence
Stranger: one
Me: Cool. What's your score?
Stranger: 15
Stranger: yours?
Me: -1
Stranger: hahaha
in the end, i guessed he was a human.
the thing said he was a robot.
is this accurate?
is it gaming the turing test to the point of breaching the spirit of the test by having the robot be the worst version of humanity as conveyed on the internet?
in other words: is the turing test meant to hypothetically carry over into non-digital media, or should we only expect it to be a useful measurement when it comes to purely digital interactions?
So I wrote texts in advance and then copy/pasted the most relevant one, ignoring what the other person said. (To look like I'm a robot.) Some of them (like in response to "how are you") that I wrote were pretty reasonable, other responses by me kind of non-sequitur.
Meanwhile, the other person acted JUST like a robot. So I picked human, since I thought they were impersonating a robot well, as requested. Not being a poorly programmed robot. (As shown.)
The game scoring needs to be updated.
By the way this is my strategy if the incentives were reasonable: I would teach the other person literally anything that I just came up with, and see if they can learn it. Robots just can't do that.
For example I might say (but I would come up with something different each time). "Okay, first I'll teach you something new that I came up with (to prove you're human to me) then you teach me something new you came up with (for me to prove I'm human to you). Absolutely anything new counts. Okay, my new thing is the game of Pirate, I just came up with it [this will be different each time.] I'll say an activity, and you tell me why pirates hate it. Doesn't matter if it's reasonable or not. Ready?"
"Yes".
"Okay, filing taxes."
"Uh ... pirates hate it because... they don't like laws? Or the government"
"Okay good now you".
"Contradict me."
"Okay."
"This game sucks."
"No it doesn't, it's great!"
"Okay we're both human haha."
"Yeah totally."
Now granted this will only work with pretty creative people who can invent a totally new game on the spot. And if any two people ever invent the same new game it might have a false positive. But on the whole I have zero doubt that it works.
I tried it with OK Google. Couldn't teach her anything.
>My strategy works really well - I start telling a role-play themed joke and if they play along they're human. This works great because it's based on common sense, entertains humans, and is a complex social performance that won't ever be the same.
But then deleted their comment. I think it's a great strategy but under the link we're discussing, why does the other person play along if they're trying to convince you they're a robot? If they play along the jig is up.
I guess maybe they meant they do that on something like Tinder (which has a lot of spambots in some geographies) rather than in this actual game.
Interlinked.
I want to measure how this affects the chats.
Me: what is your favourite flavour of chicken soup, chicken or not chicken? Them: chicken Them: what about you? Me: definitely not chicken