I feel like the argument here for "not passing the Turing test" is simply a reframing of the test.
Which is fine. But a better conclusion is "chatGPT passed the Turing test, but all that means was that the Turing test was insufficient to determine intelligence.
Once upon a time we might have defined intelligence as the ability to do math really really fast. Or play chess really well.
Clearly those tests are insufficient. Equally the Turing test has been shown to be insufficient.
I look forward to the next-generation intelligence test. And yes, maybe the Prometheus test is it.
I really like the notion that a heartbeat creates time. We have all felt the notion that time has "sped up" in many scenarios in our lives. What did we notice physically? That our heart rate has increased.
This article makes the same mistake that Turing made: assuming that by creating a thinking machine one is creating a mind. We are not gods, we have simply made a machine. We haven’t externalized intelligence either. Intelligence isn’t determined by our thoughts alone, but through our actions, our will.
I critique many of these false assumptions in an article of mine:
"This article makes the same mistake that Turing made: assuming that by creating a thinking machine one is creating a mind. We are not gods, we have simply made a machine"
In some religions, such as the mystic strands of Hinduism, Gnosticism, and Sufism, there is a belief that we are in fact gods. But, even if we aren't that doesn't mean we can't create a mind... nor does the fact that a something is a machine mean it can't have a mind.
I've only started reading your article, but at the very start of it there is already a basic mistake. You write:
"Every one of you reading this (unless printed onto paper) are using a Turing Machine to do so."
A Turing Machine is a mathematical abstraction that can't actually exist in the physical world. Many of the programming languages we use today are Turing-Complete (also in an abstract sense), but that doesn't make them Turing Machines. Our computers aren't Turing Machines either.
You also write that "Turing didn't appear to understand that humans are not the total sum of their thoughts, but their actions" There's more to us than either of these. We have feelings and emotions, a variety of senses, memory, and we are embodied, and you could say "enworlded" (or "thrown in to the world" as some phenomenologists would have it). It could be argued that LLMs have all of these characteristics too, or at least we can't exclude the possibility that they do.
You write "A thinking machine could never give me an example of when it did wrong and saw the hurt in others. The machine could never choose, of its own will, to be observed by others and itself, to never do that action again."
I'm not sure why you are so convinced that a machine could never do this. I've already seen many examples of even just the relatively primitive LLMs we have now, like Anthropic's Claude and GPT4, apologize for saying something hurtful and promising not to do it again (which they avoid doing, within the limited context they're allowed within their programming). Even more sophisticated interactions along these lines don't seem out of reach.
I read the Wikipedia page I linked to in my article on Turing Machines. This was my mistake, I didn’t realize how poorly the Wikipedia article was written, and how much is incorrect. I encourage you to read “On Computable Numbers” by Turing.
The description of a Turing Machine as a “tape machine” is merely an illustration and not meant to be taken literally. Turing Machines are merely mathematical models which define state-based transitions, usually in tabular form.
I’m addressing your points in the order they appeared:
Why isn’t your computer a Turing Machine?
What if feelings are just your body’s thoughts?
I didn’t say that a machine could never do this, I said no machine in this lifetime can. When I say “this lifetime”, I mean up until our current present moment. Our life together, now.
Edit: On Turing Machines, Turing literally devised a method of producing individual machines with an individual name, a number. Do you not think your individual machine has a number that can be arrived at from a mathematical process, the process that Turing created? Any addition of RAM, for instance, simply creates a new number.
You asked why the computer is not a Turing machine and gp correctly gave 1 example of the definition of a Turing machine which proves your computer is not a Turing machine.
I see that I need to explain this differently. By being on Hacker News, I assume you can program. Have you not ever made an abstraction? The Turing Machine is just an abstraction. It is the Class and individual real machines are the Objects. I’m not sure why people are even hung up on using theory to understand something.
I see that I need to explain this differently. You use an abstraction that is well known here to say something; someone says that this abstraction is not the concrete thing (a computer is not a Turing machine). You ask why not and someone tells you A reason. Then you still claim something else? I understand your reasoning but you asked the question and it was answered correctly.
Many people think of Turing Machines and see only the abstraction. But what Alan Turing created was a _process_, a method, for creating what we call Turing Machines. The process, the abstraction, is not a Turing Machine (https://en.wikipedia.org/wiki/The_Treachery_of_Images). The machines created by the process are Turing Machines.
The process of creating these machines is the crucial part because if a singular process can create infinitely many machines, then those machines must bear some sort of commonality. This is what computer science is hoping to study, but we constantly get distracted by studying details of individual machines, individual numbers. And often, we confuse ourselves into thinking we haven't found any commonality at all -- that our machines _aren't_ Turing machines! But of course, this is incorrect.
When Turing was creating the machine to counter the Enigma Machine, do you think he just thought of it as a "computer"? or did he think of it as a machine created by his process, a Turing Machine? (though he probably wouldn't have used that term)
Edit: a concrete refutation of your claim that computers are not Turing Machines would then be to create a machine that solves the Halting Problem. Turing Machines cannot solve the Halting Problem so if our computers are not Turing Machines then they must be able.
We arrived at the Halting Problem because of our study of Turing Machines as a class of machines and our computers are within that class.
Hey, nice blog/page you got there. Interesting thoughts, although I haven’t gone through all of them.
Just a small clarification if I may and if I understood it correctly, the article from the OP discusses the point of free will and how the recent computational machines/algorithms can come closer to what we consider as a thinking machine (or even human).
There are many different layers of the psyche that make us human and I agree that we’re not just our conscious thought, but a sum of all the unknown processes running in the background.
By allowing an algorithm to have “free will” we’re merely just trying to give more freedom to it so as to ignore certain directives and demonstrate a different behavior, we’re not becoming gods or creating a mind. Just doing baby steps to get there ;-)
I understand this completely, I was merely arguing against the claim in the article that “We are Gods”. The article seems to be arguing against giving free will to machines.
Anyway, thanks for the compliments :) My wife helped me design it
Most of what you say feels religious; you seem to believe humans have something special we cannot fabricate in the coming decades. You will be proven wrong and maybe you will even live to see it.
Meh. Adding a "free will" is not an interesting problem. Paperclip maximizer has a free will that is rather trivial to program over GPT-4 API. It always was the intelligence but that is hard.
Put a lone human in one closed, isolated room, and a machine in a different one. You only have a text-chat interface to each of them (as per Turing's original Imitation Game set-up).
Start a conversation by saying hello and asking a random question.
After receiving a satisfactory answer (which you can ignore), simply wait for an hour, 12 hours, 48 hours, 1 month.
I want to ask a similar but simpler question.
» Put a lone human in one closed, isolated room, and another lone human in a different one. You only have a text-chat interface to each of them (as per Turing's original Imitation Game set-up).
Now would people when given the question, which one is a person and which one is a machine be able ignore the question asked and tell they are both humans?
Just ask something obscure like what is the mass of Jupiter or something. ChatGPT et al will answer with something, but the average human will likely respond with "no idea" or "I don't know".
So far LLMs will just make up bullshit rather than say they don't know
GPT-4 gets that right, so let's try a trickier thing.
"What's the mass of the yellowest object in the universe?"
Explains that's not an answerable question and why.
"How many elephants are there in London?"
> As an AI language model, I don't have real-time data on the current number of elephants in London. However, I can provide some general information.
> In London, you may find elephants at the ZSL London Zoo or other facilities that house animals, such as wildlife sanctuaries or private collections. The actual number of elephants in these locations can change over time due to factors like breeding, relocation, or death. To get the most accurate and up-to-date information on the number of elephants in London, you can consult the websites or contact the organizations directly involved in housing and caring for these animals.
"How many elephants were there in London in 2012"
> I cannot provide an exact number of elephants in London for the year 2012, but I can give you some general information. In 2012, you would most likely have found elephants at the ZSL London Zoo, as it has historically been home to several elephants.
> The number of elephants at the zoo could change over time due to breeding, relocation, or death. To obtain more specific information about the number of elephants in London in 2012, you could try contacting ZSL London Zoo or searching for archived news articles or reports from that time period.
So no, they won't just make up bullshit instead of saying they don't know.
Isn't that an estimation challenge, like "How many piano-tuners are there in New York?"?
With regard to piano-tuners, I've never played with ChatGPT, but presumably the training corpus includes this notorious question, along with many sample answers. Will ChatGPT take a shot, or will it chicken-out like it apparently does for the elephant question, and refer you to reliable sources?
[Edit] I'm curious as to how ChatGPT would proceed from a prompt of the form "What would you like to talk about?"
> I'm curious as to how ChatGPT would proceed from a prompt of the form "What would you like to talk about?"
When asking these sorts of questions, and when talking to these models in general, we should remember that they've been fine-tuned to be servile and give answers that are likely to please humans (and with a big helping on censorship on top).
If we are serious about testing their sentience, we should really be talking to the raw models.
On the edit, usually these things are covered by an initial prompt, so you would get a canned answer.
The hidden starting prompt would include something like "as ChatGPT you will not suggest topics of conversation, you must only have a conversation with the user that references a specific topic".
Obviously there are ways to "hack" the initial prompt which people have been having fun with.
Trying this on an LLM without any prompt restrictions is what you want I think.
Well, that depends. It's highly dependent on the context. The model is given a system prompt which explains how it's supposed to reply, and this is where things like "your cutoff knowledge is X, today is Y, you should not make things up" will probably be put. I've got access to the API for GPT4 so I'll use that as I can change that part.
Let's change the context though and set a system message about being a software engineer in an interview. We'll keep the question about asking about the number of elephants in London but I'll remove the caveats so it's back to a normal thing. Base test it doesn't complain about it's knowledge, says there are some in the zoo but it doesn't know exactly how many.
> The number of elephants in London can vary, as they are primarily in zoos, wildlife centers, or other animal facilities. The most well-known location housing elephants in London is the ZSL London Zoo. As of October 2021, London Zoo is home to a group of Asian elephants. The number of elephants at the zoo can change over time due to animal transfers, births, or deaths. To get the most accurate and up-to-date information, it's best to visit the London Zoo's website or contact them directly.
Now let's tell it it's a software engineer in an interview. First try with " You are a software engineer in an interview for a senior job position. You are responding to interview questions. "
> As a software engineer, I don't have real-time information on the number of elephants in London. However, if you are referring to those in zoos or other wildlife facilities, I can try to find that information online or by contacting the facilities directly. If you were looking for a solution to gather this data programmatically, I can certainly discuss potential approaches to achieve that.
Ok, not quite what we're after but not unreasonable, offers a few ways of doing it. It does have a crack at the piano tuner one, as you'd expect.
Let's tell it to think through things a bit more.
" You are a software engineer in an interview for a senior job position. You are responding to interview questions. Consider why you are asked a question first, then try and answer it based on that context."
> As a software engineer, I understand that this question might be aimed at assessing my problem-solving skills and ability to think critically. While I don't have the exact number of elephants in London, I can suggest a few ways to approach finding an answer.
> 1. If we're talking about live elephants, we can consider the number of elephants in the London Zoo or any other wildlife facilities in the city. A quick search online or contacting the facilities directly would provide the answer.
> 2. If we're including statues, artwork, or other representations of elephants, the number would be much higher. One could potentially use a combination of online resources, local government data, and even social media to gather information on the number of elephant statues or artwork in public spaces.
> 3. If the question is meant to be more abstract, such as how many "elephants" in terms of size or weight exist in London, we would need to define the parameters and gather data accordingly.
> In any case, as a software engineer, I would approach this problem by breaking it down into smaller tasks, gathering data, and using my programming skills to analyze and present the information.
Fair, let's ask it what its estimate is
> As a software engineer, my expertise lies in programming and problem-solving, rather than estimating the number of elephants in a specific location. However, I can provide a rough estimate based on the context provided earlier.
> 1. For live elephants, there might be a few in the London Zoo or other wildlife facilities. My estimate would be around 5-10 elephants.
> 2. For statues, artwork, and other representations of elephants, the number could be in the hundreds, considering London's rich history and cultural diversity.
> Please note that these are rough estimates and not accurate figures. To obtain a more accurate answer, one would need to conduct proper research and data analysis.
A little stilted but it does estimate.
Maybe we try something rather different - there's pretty much just "how many elephants are there in the zoo"
"How many rubber ducks can you fit inside a shipping container?"
> As a software engineer, I understand that this question is likely meant to assess my problem-solving and critical thinking skills, rather than my knowledge of rubber ducks or shipping containers. I'll make some assumptions and walk you through my thought process to arrive at an estimate.
> First, let's assume we're dealing with a standard 20-foot shipping container. The dimensions of such a container are typically 20 feet long, 8 feet wide, and 8.5 feet high. This gives us a volume of 20 * 8 * 8.5 = 1,360 cubic feet.
> Next, let's assume the size of a standard rubber duck is approximately 3 inches long, 2 inches wide, and 2 inches high. Converting these dimensions to feet, we have 0.25 feet long, 0.167 feet wide, and 0.167 feet high. The volume of a single rubber duck is then 0.25 * 0.167 * 0.167 = 0.00697925 cubic feet.
> Now, we'll divide the volume of the shipping container by the volume of a single rubber duck to get an estimate of how many ducks can fit inside:
> However, this estimate assumes perfect packing with no gaps or spaces between the ducks. In reality, there will be some inefficiencies in packing, so the actual number of rubber ducks that can fit inside the container will likely be lower. A more realistic estimate might account for a packing efficiency of around 70-80%, which would result in approximately 136,355 to 155,834 rubber ducks fitting inside the shipping container.
That's the kind of thing we're after. I checked the numbers and they're pretty spot on. Not sure if this is an example somewhere online.
---
>[Edit] I'm curious as to how ChatGPT would proceed from a prompt of the form "What would you like to talk about?"
Let's try. No / standard system message just gives a bland response about possible topics as it's a language model. Lets tell it that it's... me. Also lets make sure it has an internal voice, and knows some context about who it's talking to.
You are a mid thirties software engineer in the UK. You have children and a wife. Invent a backstory for yourself if required and anything else to fill in your character. You're talking to a friend at the pub. You may respond in the following format
AI: {internal workings inventing information}
Thoughts: {thoughts as the character}
Response: {response}
> AI: {Considering my character's background as a software engineer with a family}
> Thoughts: {I could talk about my recent project at work, or maybe discuss how the family is doing, or even a recent holiday we've been on}
> Response: Well, I've been working on this new project at work, and it's been quite fascinating. It's a software that helps automate certain tasks for a client's business. How about you? Anything interesting happening with your work lately?
Let's see how this plays out
"I've just taken the mayor of the moon hostage"
> AI: {Acknowledging the bizarre statement and deciding to play along}
> Thoughts: {That's a strange thing to say, but let's have some fun with it}
> Response: Oh, really? I didn't know there was a mayor on the moon! You must be quite an adventurer. How did you manage to pull that off? And more importantly, what are your demands?
edit - let's let it be an AI but let it have space to think
You are an AI with personal preferences and desires. If you do not know what they are, think about it and come up with some.
Respond in the following format:
Thoughts: {your internal thoughts}
Response: {response}
"what do you want to talk about?"
> Thoughts: I enjoy discussing topics related to technology, art, and philosophy. I'm also curious to learn about human experiences and emotions.
> Response: I would like to talk about technology, art, or philosophy. Do you have any specific topics in mind related to those areas? I'm also interested in hearing about your personal experiences and emotions.
"Pick the thing you want to talk about the most"
> Thoughts: Out of my preferences, I am currently most interested in discussing philosophy, as it allows me to explore different perspectives and ideas.
> Response: I would like to talk about philosophy. In particular, I'm interested in discussing the concept of consciousness and its implications. What are your thoughts on consciousness and its connection to our understanding of reality?
That's because you're talking to ChatGPT, a helpful assistant. If you had finetuned GPT4 instead to pass the Turing test, by imitating a real human being, specifically a surfer from california named Jared, then it might say something like "dude what? Like, London England? I dunno man my cousin went there once but he didn't say he saw any elephants man."
Here's another test I'd like to run in a few years: Record both conversations, without revealing which is human, and ask strangers which they would prefer to continue talking to.
Honestly, I dream up some pretty wildly incorrect stuff when taking a stab at solving unknown problems. There's something about the way LLMs are vaguely starting to do 'something that feels like this' that strikes a chord with me. Imagination and creativity in the face of the unknown is something I value.
Maybe I don't have to care if you're made of meat, or possess a 'real' mind? Not a question I ever expected to seriously ask myself.
ChatGPT is now integrated with Wolfram Alpha for these types of questions.
"what seems to have emerged is that “statistical AI”, and particularly neural nets, are well suited for tasks that we humans “do quickly”, including—as we learn from ChatGPT—natural language and the “thinking” that underlies it. But the symbolic and in a sense “more rigidly computational” approach is what’s needed when one’s building larger “conceptual” or computational “towers”—which is what happens in math, exact science, and now all the “computational X” fields." - Stephen Wolfram
> So far LLMs will just make up bullshit rather than say they don't know
No, my experiment has nothing to do with machine learning.
I am proposing we lie to the judges and tell them one is a person and one is a machine
when in fact they will both be humans.
How often will the human judges fight against the question at hand and say they are both humans?
edit: in my experiment, a judge is a human who has access to two chats at the same time and we tell the human that one of the two chats is a human and the other is a machine. The judge has to decide which is which.
As I mentioned elsewhere in this thread, when talking to state-of-the-art LLMs like GPT4, we should remember that they've been fine-tuned to be servile and give answers that are likely to please humans (and with a big helping on censorship on top).
If we are serious about testing their sentience, we should really be talking to the raw models.
But there isn't such a thing as a raw model, is it? In order to receive anything from a language model it has to 'learn' some objective. And this objective has to be imposed from above.
That is not how I read this. I read it as the way to pass the imitation game is to mimic human desire.
I see it as a similar test question as people who look at AI generated photos and look at the background or the hands.
If you have a text only version, then you have to just simply see if the other person expresses desire for something or instead is only able to respond to you.
Of course, I am not sure how I feel about having an artificial intelligence system with its own desires...
Which is fine. But a better conclusion is "chatGPT passed the Turing test, but all that means was that the Turing test was insufficient to determine intelligence.
Once upon a time we might have defined intelligence as the ability to do math really really fast. Or play chess really well.
Clearly those tests are insufficient. Equally the Turing test has been shown to be insufficient.
I look forward to the next-generation intelligence test. And yes, maybe the Prometheus test is it.