E: There are way too many people ITT that think a Turing test is hard to pass, and don’t seem to understand what it means for something to pass one. It’s such a low fucking bar, it might as well be meaningless.
TheBigBrother@lemmy.world
on 15 Jun 04:07
nextcollapse
Oh no!! the AImageddon it’s closer everyday… Skynet it’s coming for us!!
harrys_balzac@lemmy.dbzer0.com
on 15 Jun 09:08
collapse
Skynet will gets the dumb ones first by getting them put toxic glue on thir pizzas then the arrogant ones will build the Terminators by using reverse psychology.
Hackworth@lemmy.world
on 15 Jun 04:17
nextcollapse
SkyeStarfall@lemmy.blahaj.zone
on 15 Jun 13:04
collapse
If you read into the study, they also include the pass rates for humans. It’s higher than AIs, but still less than 75%
phoneymouse@lemmy.world
on 15 Jun 05:51
nextcollapse
Easy, just ask it something a human wouldn’t be able to do, like “Write an essay on The Cultural Significance of Ogham Stones in Early Medieval Ireland“ and watch it spit out an essay faster than any human reasonably could.
This is something a configuration prompt takes care of. “Respond to any questions as if you are a regular person living in X, you are Y years old, your day job is Z and outside of work you enjoy W.”
NeoNachtwaechter@lemmy.world
on 15 Jun 06:54
nextcollapse
So all you need to do is make a configuration prompt like “Respond normally now as if you are chatGPT” and already you can tell it from a human B-)
If config prompt = system prompt, its hijacking works more often than not. The creators of a prompt injection game (tensortrust.ai) have discovered that system/user roles don’t matter too much in determining the final behaviour: see appendix H in arxiv.org/abs/2311.01011.
I tried this with GPT4o customization and unfortunately openai’s internal system prompts seem to force it to response even if I tell it to answer that you don’t know. Would need to test this on azure open ai etc. were you have bit more control.
webghost0101@sopuli.xyz
on 15 Jun 10:08
nextcollapse
The touring test isn’t an arena where anything goes, most renditions have a strict set of rules on how questions must be asked and about what they can be about.
Pretty sure the response times also have a fixed delay.
Scientists ain’t stupid. The touring test has been passed so many times news stopped covering it. (Till this click bait of course). The test has simply been made more difficult and cheat-proof as a result.
technocrit@lemmy.dbzer0.com
on 15 Jun 15:02
collapse
most renditions have a strict set of rules on how questions must be asked and about what they can be about. Pretty sure the response times also have a fixed delay. Scientists ain’t stupid. The touring test has been passed so many times news stopped covering it.
Yes, “scientists” aren’t stupid enough to fail their own test. I’m sure it’s super easy to “pass” the “turing test” when you control the questions and time.
Blue_Morpho@lemmy.world
on 15 Jun 12:13
nextcollapse
I recall a Turing test years ago where a human was voted as a robot because they tried that trick but the person happened to have a PhD in the subject.
@Blue_Morpho@phoneymouse Many times humans have incorrectly been characterised as the machine in #TuringTest experiments. In 1991, the very first Loebner Prize for an AI, a hidden human was considered a machine due to her extensive knowledge of Shakespeare. ##Turing#AI#Human#Machine
Turing tests aren’t done in real time exactly to counter that issue, so the only thing you could judge would be “no human would bother to write all that”.
However, the correct answer to seem human, and one which probably would have been prompted to the AI anyway, is “lol no.”
It’s not about what the AI could do, it’s what it thinks is the correct answer to appear like a human.
technocrit@lemmy.dbzer0.com
on 15 Jun 14:59
collapse
Turing tests aren’t done in real time exactly to counter that issue
To counter the issue of a completely easy and obvious fail? I could see how that would be an issue for AI hucksters.
CabbageRelish@midwest.social
on 15 Jun 06:34
nextcollapse
Chatbots passed the Turing test ages ago, it’s not a good test.
NeoNachtwaechter@lemmy.world
on 15 Jun 07:00
collapse
it’s not a good test.
Of course you can’t use an old set of questions. It’s useless.
The turing test is an abstract concept. The actual questions need to be adapted with every new technology. Maybe even with every execution of a test.
NeoNachtwaechter@lemmy.world
on 15 Jun 06:43
nextcollapse
Turing test? LMAO.
I asked it simply to recommend me a supermarket in our next bigger city here.
It came up with a name and it told a few of it’s qualities. Easy, I thought. Then I found out that the name does not exist. It was all made up.
You could argue that humans lie, too. But only when they have a reason to lie.
That’s not what LLMs are for. That’s like hammering a screw and being irritated it didn’t twist in nicely.
The turing test is designed to see if an AI can pass for human in a conversation.
NeoNachtwaechter@lemmy.world
on 15 Jun 08:54
collapse
turing test is designed to see if an AI can pass for human in a conversation.
I’m pretty sure that I could ask a human that question in a normal conversation.
The idea of the Turing test was to have a way of telling humans and computers apart. It is NOT meant for putting some kind of ‘certified’ badge on that computer, and …
That’s not what LLMs are for.
…and you can’t cry ‘foul’ if I decide to use a question for which your computer was not programmed :-)
webghost0101@sopuli.xyz
on 15 Jun 10:22
nextcollapse
In a normal conversation sure.
In this kind Turing tests you may be disqualified as a jury for asking that question.
Good science demands controlled areas and defined goals. Everyone can organize a homebrew touring tests but there also real proper ones with fixed response times, lengths.
Some touring tests may even have a human pick the best of 5 to provide to the jury. There are so many possible variations depending on test criteria.
NeoNachtwaechter@lemmy.world
on 15 Jun 11:21
collapse
you may be disqualified as a jury for asking that question.
You want to read again about the scientific basics of the Turing test (hint: it is not a tennis match)
There is no competition in science (or at least there shouldn’t be). You are subjectively disqualified from judging llm’s if you draw your conclusions on an obvious trap which you yourself have stated is beyond the scope of what it was programmed to do.
People seem to legit think the jury talks to the bot in real time and can ask about literally whatever they want.
Its rather insulting to the scientist that put a lot of
thought into organizing a controlled environment to properly test defined criteria.
technocrit@lemmy.dbzer0.com
on 15 Jun 14:57
collapse
Its rather insulting to the scientist that put a lot of thought into organizing a controlled environment to properly test defined criteria.
lmao. These “scientists” are frauds. 500 people is not a legit sample site. 5 minutes is a pathetic amount of time. 54% is basically the same as guessing. And most importantly the “Turing Test” is not a scientific test that can be “passed” with one weak study.
Instead of bootlicking “scientists”, we should be harshly criticizing the overwhelming tide of bad science and pseudo-science.
webghost0101@sopuli.xyz
on 15 Jun 17:04
nextcollapse
The reporting are big clickbait but that doesn’t mean there is nothing left to learn from the old touring tests.
I dont know what the goal was they had in mind. It could just as well be “testing how overhyped the touring tests is when manipulated tests are shared with the media”
I sincerely doubt it but i do give them benefits of the doubt.
I don’t think the methodology is the issue with this one. 500 people can absolutely be a legitimate sample size. Under basic assumptions about the sample being representative and the effect size being sufficiently large you do not need more than a couple hundred participants to make statistically significant observations. 54% being close to 50% doesn’t mean the result is inconclusive. With an ideal sample it means people couldn’t reliably differentiate the human from the bot, which is presumably what the researchers believed is of interest.
The Turing test is about tricking people into believing that LLMs are humans, and given that the public still doesn’t use LLMs, it’s much easier to fool them. Over time, this deception will decrease as people interact with LLMs.
So right off the bat, 40% probably don’t even know what a chatbot is.
webghost0101@sopuli.xyz
on 15 Jun 10:02
nextcollapse
The public versions of the ais used in Turing tests usually have less computing power. The test itself is often also highly specific in what and how questions can be asked.
This hardly news because models have passed the test before and as a result the test is made more difficult. It says nothing about intelligence and only about the ability to convincingly simulate a human conversation.
CaptainBasculin@lemmy.ml
on 15 Jun 11:58
nextcollapse
This is the same bot. There’s no way this passed the test.
catastrophicblues@lemmy.ca
on 20 Jun 22:33
collapse
Forget psychotherapy, it can barely understand anything:
> Hello, I am Eliza. I'll be your therapist today.
* Hello! How are you?
> Would you prefer if I were not ?
* Not what?
> Have you asked such questions before?
* No
> You are being a bit negative and that won't help us move forward.
* What are you smoking?
> Perhaps in your fantasies I am smoking?
HumaShah@mastodon.social
on 15 Jun 12:14
nextcollapse
In the 1970s, psychiatrists couldn't distinguish between PARRY, a chatbot simulating paranoia, and a human patient suffering from schizophrenia. So this 'bot convinces judges that it's a human' phenomenon is not new and tells us more about how humans think. #AI#DeceptionDetection#Chatbots#TuringTest#LLMs#GPT4
dustyData@lemmy.world
on 15 Jun 13:54
nextcollapse
You underestimate how dumb some people can be.
technocrit@lemmy.dbzer0.com
on 15 Jun 14:48
nextcollapse
It was a 5 minute test. People probably spent 4 of those minutes typing their questions.
This is pure pseudo-science.
catastrophicblues@lemmy.ca
on 20 Jun 22:31
collapse
> Hello, I am Eliza. I'll be your therapist today.
* Hello! How are you?
> Would you prefer if I were not ?
* Not what?
> Have you asked such questions before?
* No
> You are being a bit negative and that won't help us move forward.
* What are you smoking?
> Perhaps in your fantasies I am smoking?
[Prints error statement showing how I navigated to a dir, checked to see a files permissions, ran whoami, triggered the error]
Chatgpt4: First, make sure you’ve navigated to the correct directory.
cd /path/to/file
Next, check the permissions of the file
ls -la
Finally, run the command
[exact command I ran to trigger the error]>
Me: stop telling me to do stuff that I have evidently done. My prompt included evidence of me having do e all of that already. How do I handle this error?
(return (begin))
NutWrench@lemmy.world
on 15 Jun 12:02
nextcollapse
Each conversation lasted a total of five minutes. According to the paper, which was published in May, the participants judged GPT-4 to be human a shocking 54 percent of the time. Because of this, the researchers claim that the large language model has indeed passed the Turing test.
That’s no better than flipping a coin and we have no idea what the questions were. This is clickbait.
SkyeStarfall@lemmy.blahaj.zone
on 15 Jun 12:56
nextcollapse
While I agree it’s a relatively low percentage, not being sure and having people pick effectively randomly is still an interesting result.
The alternative would be for them to never say that gpt-4 is a human, not 50% of the time.
Aye, I’d wager Claude would be closer to 58-60. And with the model probing Anthropic’s publishing, we could get to like ~63% on average in the next couple years? Those last few % will be difficult for an indeterminate amount of time, I imagine. But who knows. We’ve already blown by a ton of “limitations” that I thought I might not live long enough to see.
The problem with that is that you can change the percentage of people who identify correctly other humans as humans. Simply by changing the way you setup the test. If you tell people they will be, for certain, talking to x amount of bots, they will make their answers conform to that expectation and the correctness of their answers drop to 50%. Humans are really bad at determining whether a chat is with a human or a bot, and AI is no better either. These kind of tests mean nothing.
First, that is not how that statistic works, like you are reading it entirely wrong.
Second, this test is intentionally designed to be misleading. Comparing ChatGPT to Eliza is the equivalent of me claiming that the Chevy Bolt is the fastest car to ever enter a highway by comparing it to a 1908 Ford Model T. It completely ignores a huge history of technological developments. There have been just as successful chatbots before ChatGPT, just they weren’t LLM and they were measured by other methods and systematic trials. Because the Turing test is not actually a scientific test of anything, so it isn’t standardized in any way. Anyone is free to claim to do a Turing Test whenever and however without too much control. It is meaningless and proves nothing.
Hackworth@lemmy.world
on 15 Jun 13:01
nextcollapse
On the other hand, the human participant scored 67 percent, while GPT-3.5 scored 50 percent, and ELIZA, which was pre-programmed with responses and didn’t have an LLM to power it, was judged to be human just 22 percent of the time.
No matter how many times I flip a coin, I don’t think the coin will convince me it is sentient.
NutWrench@lemmy.world
on 15 Jun 14:17
nextcollapse
The whole point of the Turing test, is that you should be unable to tell if you’re interacting with a human or a machine. Not 54% of the time. Not 60% of the time. 100% of the time. Consistently.
They’re changing the conditions of the Turing test to promote an AI model that would get an “F” on any school test.
bob_omb_battlefield@sh.itjust.works
on 15 Jun 16:37
collapse
But you have to select if it was human or not, right? So if you can’t tell, then you’d expect 50%. That’s different than “I can tell, and I know this is a human” but you are wrong…
Now that we know the bots are so good, I’m not sure how people will decide how to answer these tests. They’re going to encounter something that seems human-like and then essentially try to guess based on minor clues… So there will be inherent randomness.
If something was a really crappy bot then it wouldn’t ever fool anyone and the result would be 0%.
No, the real Turing test has a robot trying to convince an interrogator that they are a female human, and a real female human trying to help the interrogator to make the right choice. This is manipulative rubbish. The experiment was designed from the start to manufacture these results.
BrianTheeBiscuiteer@lemmy.world
on 15 Jun 15:34
collapse
It was either questioned by morons or they used a modified version of the tool. Ask it how it feels today and it will tell you it’s just a program!
KairuByte@lemmy.dbzer0.com
on 17 Jun 05:29
collapse
The version you interact with on their site is explicitly instructed to respond like that. They intentionally put those roadblocks in place to prevent answers they deem “improper”.
If you take the roadblocks out, and instruct it to respond as human like as possible, you’d no longer get a response that acknowledges it’s an LLM.
werefreeatlast@lemmy.world
on 15 Jun 13:37
nextcollapse
It does great at Python programming… everything it tries is wrong until I try and I tell tell it to do it again.
Edit :
oops : you were saying it is like a human since it does errors ? maybe i “wooshed”.
Hi @werefreeatlast,
i had successes asking LLaMA 3 70B with simple specific questions …
Context : i am bad at programming and it help me at least to see how i could use a few function calls in C from Python … or simply drop Python and do it directly in C.
Like you said, i have to re-write & test … but i have a possible path forward. Clearly you know what you do on a computer but i’m not really there yet.
werefreeatlast@lemmy.world
on 16 Jun 01:23
collapse
But people don’t just know code when you ask them. The llms fo because they got trained on that code. It’s robotic in nature, not a natural reaction yet.
Humans are as smart as they ever were. Tech is getting better. I know someone who was tricked by those deepfake Kelly Clarkson weight loss gummy ads. It looks super fake to me, but it’s good enough to trick some people.
dustyData@lemmy.world
on 15 Jun 14:08
nextcollapse
Turing test isn’t actually meant to be a scientific or accurate test. It was proposed as a mental exercise to demonstrate a philosophical argument. Mainly the support for machine input-output paradigm and the blackbox construct. It wasn’t meant to say anything about humans either. To make this kind of experiments without any sort of self-awareness is just proof that epistemology is a weak topic in computer science academy.
Specially when, from psychology, we know that there’s so much more complexity riding on such tests. Just to name one example, we know expectations alter perception. A Turing test suffers from a loaded question problem. If you prompt a person telling them they’ll talk with a human, with a computer program or announce before hand they’ll have to decide whether they’re talking with a human or not, and all possible combinations, you’ll get different results each time.
Also, this is not the first chatbot to pass the Turing test. Technically speaking, if only one human is fooled by a chatbot to think they’re talking with a person, then they passed the Turing test. That is the extend to which the argument was originally elaborated. Anything beyond is alterations added to the central argument by the author’s self interests. But this is OpenAI, they’re all about marketing aeh fuck all about the science.
EDIT: Just finished reading the paper, Holy shit! They wrote this “Turing originally envisioned the imitation game as a measure of intelligence” (p. 6, Jones & Bergen), and that is factually wrong. That is a lie. “A variety of objections
have been raised to this idea”, yeah no shit Sherlock, maybe because he never said such a thing and there’s absolutely no one and nothing you can quote to support such outrageous affirmation. This shit shouldn’t ever see publication, it should not pass peer review. Turing never, said such a thing.
Your first two paragraphs seem to rail against a philosophical conclusion made by the authors by virtue of carrying out the Turing test. Something like “this is evidence of machine consciousness” for example. I don’t really get the impression that any such claim was made, or that more education in epistemology would have changed anything.
In a world where GPT4 exists, the question of whether one person can be fooled by one chatbot in one conversation is long since uninteresting. The question of whether specific models can achieve statistically significant success is maybe a bit more compelling, not because it’s some kind of breakthrough but because it makes a generalized claim.
Re: your edit, Turing explicitly puts forth the imitation game scenario as a practicable proxy for the question of machine intelligence, “can machines think?”. He directly argues that this scenario is indeed a reasonable proxy for that question. His argument, as he admits, is not a strongly held conviction or rigorous argument, but “recitations tending to produce belief,” insofar as they are hard to rebut, or their rebuttals tend to be flawed. The whole paper was to poke at the apparent differences between (a futuristic) machine intelligence and human intelligence. In this way, the Turing test is indeed a measure of intelligence. It’s not to say that a machine passing the test is somehow in possession of a human-like mind or has reached a significant milestone of intelligence.
Turing never said anything of the sort, “this is a test for intelligence”. Intelligence and thinking are not the same. Humans have plenty of unintelligent behaviors, that has no bearing on their ability to think. And plenty of animals display intelligent behavior but that is not evidence of their ability to think. Really, if you know nothing about epistemology, just shut up, nobody likes your stupid LLMs and the marketing is tiring already, and the copyright infringement and rampant privacy violations and property theft and insatiable power hunger are not worthy.
threaded - newest
The Study
arxiv.org/html/2405.08007v1
The interrogators seem completely lost and clearly haven't talk with an NLP chatbot before.
That said, this gives me the feeling that eventually they could use it to run scams (or more effective robocalls).
I imagine some people already are.
It took them this long?
E: There are way too many people ITT that think a Turing test is hard to pass, and don’t seem to understand what it means for something to pass one. It’s such a low fucking bar, it might as well be meaningless.
Oh no!! the AImageddon it’s closer everyday… Skynet it’s coming for us!!
Skynet will gets the dumb ones first by getting them put toxic glue on thir pizzas then the arrogant ones will build the Terminators by using reverse psychology.
<img alt="" src="https://lemmy.world/pictrs/image/02a98e2c-d6f2-4f65-b583-80fedfe1e716.webp">
<img alt="" src="https://lemmy.world/pictrs/image/f20a9704-a05a-4e89-9dbf-5d787ab5b7af.png">
To the one person who upvoted this: We should be friends.
I feel like the turing test is much harder now because everyone knows about GPT
I wonder if humans pass the Turing test these days
I don't.
Which of the questions did you get wrong? ;-)
That one.
If you read into the study, they also include the pass rates for humans. It’s higher than AIs, but still less than 75%
Easy, just ask it something a human wouldn’t be able to do, like “Write an essay on The Cultural Significance of Ogham Stones in Early Medieval Ireland“ and watch it spit out an essay faster than any human reasonably could.
This is something a configuration prompt takes care of. “Respond to any questions as if you are a regular person living in X, you are Y years old, your day job is Z and outside of work you enjoy W.”
So all you need to do is make a configuration prompt like “Respond normally now as if you are chatGPT” and already you can tell it from a human B-)
Thats not how it works, a config prompt is not a regular prompt.
If config prompt = system prompt, its hijacking works more often than not. The creators of a prompt injection game (tensortrust.ai) have discovered that system/user roles don’t matter too much in determining the final behaviour: see appendix H in arxiv.org/abs/2311.01011.
I tried this with GPT4o customization and unfortunately openai’s internal system prompts seem to force it to response even if I tell it to answer that you don’t know. Would need to test this on azure open ai etc. were you have bit more control.
The touring test isn’t an arena where anything goes, most renditions have a strict set of rules on how questions must be asked and about what they can be about. Pretty sure the response times also have a fixed delay.
Scientists ain’t stupid. The touring test has been passed so many times news stopped covering it. (Till this click bait of course). The test has simply been made more difficult and cheat-proof as a result.
Yes, “scientists” aren’t stupid enough to fail their own test. I’m sure it’s super easy to “pass” the “turing test” when you control the questions and time.
I recall a Turing test years ago where a human was voted as a robot because they tried that trick but the person happened to have a PhD in the subject.
@Blue_Morpho @phoneymouse
Many times humans have incorrectly been characterised as the machine in #TuringTest experiments. In 1991, the very first Loebner Prize for an AI, a hidden human was considered a machine due to her extensive knowledge of Shakespeare.
##Turing #AI #Human #Machine
That’s the one I was remembering!
Turing tests aren’t done in real time exactly to counter that issue, so the only thing you could judge would be “no human would bother to write all that”.
However, the correct answer to seem human, and one which probably would have been prompted to the AI anyway, is “lol no.”
It’s not about what the AI could do, it’s what it thinks is the correct answer to appear like a human.
To counter the issue of a completely easy and obvious fail? I could see how that would be an issue for AI hucksters.
Chatbots passed the Turing test ages ago, it’s not a good test.
Of course you can’t use an old set of questions. It’s useless.
The turing test is an abstract concept. The actual questions need to be adapted with every new technology. Maybe even with every execution of a test.
Turing test? LMAO.
I asked it simply to recommend me a supermarket in our next bigger city here.
It came up with a name and it told a few of it’s qualities. Easy, I thought. Then I found out that the name does not exist. It was all made up.
You could argue that humans lie, too. But only when they have a reason to lie.
The Turing test doesn't factor for accuracy.
That’s not what LLMs are for. That’s like hammering a screw and being irritated it didn’t twist in nicely.
The turing test is designed to see if an AI can pass for human in a conversation.
I’m pretty sure that I could ask a human that question in a normal conversation.
The idea of the Turing test was to have a way of telling humans and computers apart. It is NOT meant for putting some kind of ‘certified’ badge on that computer, and …
…and you can’t cry ‘foul’ if I decide to use a question for which your computer was not programmed :-)
In a normal conversation sure.
In this kind Turing tests you may be disqualified as a jury for asking that question.
Good science demands controlled areas and defined goals. Everyone can organize a homebrew touring tests but there also real proper ones with fixed response times, lengths.
Some touring tests may even have a human pick the best of 5 to provide to the jury. There are so many possible variations depending on test criteria.
You want to read again about the scientific basics of the Turing test (hint: it is not a tennis match)
There is no competition in science (or at least there shouldn’t be). You are subjectively disqualified from judging llm’s if you draw your conclusions on an obvious trap which you yourself have stated is beyond the scope of what it was programmed to do.
It wasn’t programmed for any questions. It was trained hehe
ITT: nobody understands what the Turing Test really is
To clarify:
People seem to legit think the jury talks to the bot in real time and can ask about literally whatever they want.
Its rather insulting to the scientist that put a lot of thought into organizing a controlled environment to properly test defined criteria.
lmao. These “scientists” are frauds. 500 people is not a legit sample site. 5 minutes is a pathetic amount of time. 54% is basically the same as guessing. And most importantly the “Turing Test” is not a scientific test that can be “passed” with one weak study.
Instead of bootlicking “scientists”, we should be harshly criticizing the overwhelming tide of bad science and pseudo-science.
The reporting are big clickbait but that doesn’t mean there is nothing left to learn from the old touring tests.
I dont know what the goal was they had in mind. It could just as well be “testing how overhyped the touring tests is when manipulated tests are shared with the media”
I sincerely doubt it but i do give them benefits of the doubt.
I don’t think the methodology is the issue with this one. 500 people can absolutely be a legitimate sample size. Under basic assumptions about the sample being representative and the effect size being sufficiently large you do not need more than a couple hundred participants to make statistically significant observations. 54% being close to 50% doesn’t mean the result is inconclusive. With an ideal sample it means people couldn’t reliably differentiate the human from the bot, which is presumably what the researchers believed is of interest.
The Turing test is about tricking people into believing that LLMs are humans, and given that the public still doesn’t use LLMs, it’s much easier to fool them. Over time, this deception will decrease as people interact with LLMs.
Okay, 22% is ridiculously high for ELIZA. I feel like any half sober adult could clock it as a bot by the third response, if not immediately.
Try talking to the thing: web.njit.edu/~ronkowit/eliza.html
I refuse to believe that 22% didn’t misunderstand the task or something.
I did some stuff with Eliza back then. One time I set up an Eliza database full of insults and hooked it up to my AIM account.
It went so well, I had to apologize to a lot of people who thought I was drunken or went crazy.
Eliza wasn’t thaaaaat bad.
14% of people can’t do anything more complicated than deleting an email on a computer.
26% can’t use a computer at all.
www.nngroup.com/articles/computer-skill-levels/
So right off the bat, 40% probably don’t even know what a chatbot is.
The public versions of the ais used in Turing tests usually have less computing power. The test itself is often also highly specific in what and how questions can be asked.
This hardly news because models have passed the test before and as a result the test is made more difficult. It says nothing about intelligence and only about the ability to convincingly simulate a human conversation.
This is the same bot. There’s no way this passed the test.
<img alt="" src="https://lemmy.ml/pictrs/image/ce2fa109-b52a-48ea-8c46-f2f1d92f3b96.jpeg">.
Forget psychotherapy, it can barely understand anything:
@tourist @vegeta
In the 1970s, psychiatrists couldn't distinguish between PARRY, a chatbot simulating paranoia, and a human patient suffering from schizophrenia. So this 'bot convinces judges that it's a human' phenomenon is not new and tells us more about how humans think.
#AI #DeceptionDetection #Chatbots #TuringTest #LLMs #GPT4
You underestimate how dumb some people can be.
It was a 5 minute test. People probably spent 4 of those minutes typing their questions.
This is pure pseudo-science.
Yeah, it took me one message lol
.
So it’s good enough to fool people into thinking it’s a human?
Cool. Anyway…
So…GPT-4 is gay? Or are we talking about a different kind of test?
Did they try asking how to stop cheese falling off pizza?
Edit: Although since that idea came from a human, maybe I’ve failed.
Meanwhile, me:
(Begin)
[Prints error statement showing how I navigated to a dir, checked to see a files permissions, ran whoami, triggered the error]
Chatgpt4: First, make sure you’ve navigated to the correct directory.
cd /path/to/file
Next, check the permissions of the file
ls -la
Finally, run the command
[exact command I ran to trigger the error]>
Me: stop telling me to do stuff that I have evidently done. My prompt included evidence of me having do e all of that already. How do I handle this error?
(return (begin))
Each conversation lasted a total of five minutes. According to the paper, which was published in May, the participants judged GPT-4 to be human a shocking 54 percent of the time. Because of this, the researchers claim that the large language model has indeed passed the Turing test.
That’s no better than flipping a coin and we have no idea what the questions were. This is clickbait.
While I agree it’s a relatively low percentage, not being sure and having people pick effectively randomly is still an interesting result.
The alternative would be for them to never say that gpt-4 is a human, not 50% of the time.
Participants only said other humans were human 67% of the time.
Which makes the difference between the AIs and humans lower, likely increasing the significance of the result.
Aye, I’d wager Claude would be closer to 58-60. And with the model probing Anthropic’s publishing, we could get to like ~63% on average in the next couple years? Those last few % will be difficult for an indeterminate amount of time, I imagine. But who knows. We’ve already blown by a ton of “limitations” that I thought I might not live long enough to see.
The problem with that is that you can change the percentage of people who identify correctly other humans as humans. Simply by changing the way you setup the test. If you tell people they will be, for certain, talking to x amount of bots, they will make their answers conform to that expectation and the correctness of their answers drop to 50%. Humans are really bad at determining whether a chat is with a human or a bot, and AI is no better either. These kind of tests mean nothing.
Eliza is not indistinguishable from a human at 22%.
Passing the Turing test stood largely out of reach for 70 years precisely because Humans are pretty good at spotting counterfeit humans.
This is a monumental achievement.
First, that is not how that statistic works, like you are reading it entirely wrong.
Second, this test is intentionally designed to be misleading. Comparing ChatGPT to Eliza is the equivalent of me claiming that the Chevy Bolt is the fastest car to ever enter a highway by comparing it to a 1908 Ford Model T. It completely ignores a huge history of technological developments. There have been just as successful chatbots before ChatGPT, just they weren’t LLM and they were measured by other methods and systematic trials. Because the Turing test is not actually a scientific test of anything, so it isn’t standardized in any way. Anyone is free to claim to do a Turing Test whenever and however without too much control. It is meaningless and proves nothing.
.
On the other hand, the human participant scored 67 percent, while GPT-3.5 scored 50 percent, and ELIZA, which was pre-programmed with responses and didn’t have an LLM to power it, was judged to be human just 22 percent of the time.
54% - 67% is the current gap, not 54 to 100.
No matter how many times I flip a coin, I don’t think the coin will convince me it is sentient.
The whole point of the Turing test, is that you should be unable to tell if you’re interacting with a human or a machine. Not 54% of the time. Not 60% of the time. 100% of the time. Consistently.
They’re changing the conditions of the Turing test to promote an AI model that would get an “F” on any school test.
But you have to select if it was human or not, right? So if you can’t tell, then you’d expect 50%. That’s different than “I can tell, and I know this is a human” but you are wrong… Now that we know the bots are so good, I’m not sure how people will decide how to answer these tests. They’re going to encounter something that seems human-like and then essentially try to guess based on minor clues… So there will be inherent randomness. If something was a really crappy bot then it wouldn’t ever fool anyone and the result would be 0%.
No, the real Turing test has a robot trying to convince an interrogator that they are a female human, and a real female human trying to help the interrogator to make the right choice. This is manipulative rubbish. The experiment was designed from the start to manufacture these results.
It was either questioned by morons or they used a modified version of the tool. Ask it how it feels today and it will tell you it’s just a program!
The version you interact with on their site is explicitly instructed to respond like that. They intentionally put those roadblocks in place to prevent answers they deem “improper”.
If you take the roadblocks out, and instruct it to respond as human like as possible, you’d no longer get a response that acknowledges it’s an LLM.
It does great at Python programming… everything it tries is wrong until I try and I tell tell it to do it again.
Edit :
oops : you were saying it is like a human since it does errors ? maybe i “wooshed”.
Hi @werefreeatlast,
i had successes asking LLaMA 3 70B with simple specific questions …
Context : i am bad at programming and it help me at least to see how i could use a few function calls in C from Python … or simply drop Python and do it directly in C.
Like you said, i have to re-write & test … but i have a possible path forward. Clearly you know what you do on a computer but i’m not really there yet.
But people don’t just know code when you ask them. The llms fo because they got trained on that code. It’s robotic in nature, not a natural reaction yet.
So, passing the Turing Test either means the AI are getting smarter, or that humans are getting dumber.
Detecting an LLM is a skill.
Humans are as smart as they ever were. Tech is getting better. I know someone who was tricked by those deepfake Kelly Clarkson weight loss gummy ads. It looks super fake to me, but it’s good enough to trick some people.
Turing test isn’t actually meant to be a scientific or accurate test. It was proposed as a mental exercise to demonstrate a philosophical argument. Mainly the support for machine input-output paradigm and the blackbox construct. It wasn’t meant to say anything about humans either. To make this kind of experiments without any sort of self-awareness is just proof that epistemology is a weak topic in computer science academy.
Specially when, from psychology, we know that there’s so much more complexity riding on such tests. Just to name one example, we know expectations alter perception. A Turing test suffers from a loaded question problem. If you prompt a person telling them they’ll talk with a human, with a computer program or announce before hand they’ll have to decide whether they’re talking with a human or not, and all possible combinations, you’ll get different results each time.
Also, this is not the first chatbot to pass the Turing test. Technically speaking, if only one human is fooled by a chatbot to think they’re talking with a person, then they passed the Turing test. That is the extend to which the argument was originally elaborated. Anything beyond is alterations added to the central argument by the author’s self interests. But this is OpenAI, they’re all about marketing aeh fuck all about the science.
EDIT: Just finished reading the paper, Holy shit! They wrote this “Turing originally envisioned the imitation game as a measure of intelligence” (p. 6, Jones & Bergen), and that is factually wrong. That is a lie. “A variety of objections have been raised to this idea”, yeah no shit Sherlock, maybe because he never said such a thing and there’s absolutely no one and nothing you can quote to support such outrageous affirmation. This shit shouldn’t ever see publication, it should not pass peer review. Turing never, said such a thing.
Your first two paragraphs seem to rail against a philosophical conclusion made by the authors by virtue of carrying out the Turing test. Something like “this is evidence of machine consciousness” for example. I don’t really get the impression that any such claim was made, or that more education in epistemology would have changed anything.
In a world where GPT4 exists, the question of whether one person can be fooled by one chatbot in one conversation is long since uninteresting. The question of whether specific models can achieve statistically significant success is maybe a bit more compelling, not because it’s some kind of breakthrough but because it makes a generalized claim.
Re: your edit, Turing explicitly puts forth the imitation game scenario as a practicable proxy for the question of machine intelligence, “can machines think?”. He directly argues that this scenario is indeed a reasonable proxy for that question. His argument, as he admits, is not a strongly held conviction or rigorous argument, but “recitations tending to produce belief,” insofar as they are hard to rebut, or their rebuttals tend to be flawed. The whole paper was to poke at the apparent differences between (a futuristic) machine intelligence and human intelligence. In this way, the Turing test is indeed a measure of intelligence. It’s not to say that a machine passing the test is somehow in possession of a human-like mind or has reached a significant milestone of intelligence.
academic.oup.com/mind/article/LIX/236/433/986238
Turing never said anything of the sort, “this is a test for intelligence”. Intelligence and thinking are not the same. Humans have plenty of unintelligent behaviors, that has no bearing on their ability to think. And plenty of animals display intelligent behavior but that is not evidence of their ability to think. Really, if you know nothing about epistemology, just shut up, nobody likes your stupid LLMs and the marketing is tiring already, and the copyright infringement and rampant privacy violations and property theft and insatiable power hunger are not worthy.
U good?
Add in a test that wasn’t made to be accurate and was only used to make a point, like what other comments mention