If someone gave me the Turing test, they would think I was a machine.

I took a linguistics class with a professor who'd worked on very early language software, trying to teach computers how grammar works in the 70s. They thought it would be the simple, given how mathematically language tends to be, but when they started working with them they discovered that the social and idiopathic nature of language made it virtually impossible.

I just love how Professor Brailsford explains stuff :)

Me: My name is Ron AI: Hello Me: Whats my name?\ AI: Your name is cat.

I really like David Deutsch’s comment on the Turing test: in one of his popular books, he said that the approach of simulating a human chatting is in no way moving us closer to simulating a human thinking. the problem (he said) is that we lack an _explanation_ of what consciousness is. if we had one, then at worst a very slow AI could be produced, and could have been produced on equipment that is obsolete now.

Professor Brailsford is great, he's so passionate that you can't help but be interested!

I would love to see this interview updated.

I remember watching (on TV) a documentary about Deep Blue, and they SPECIFICALLY clarified that unlike other computers at the time, Deep Blue did NOT simply examine all possible combinations for the next few turns, and pick the one that turns out best at the end of them. Instead, it tried to narrow down the LIKELY combinations the opponent was to make in response to its next move (out of all moves that IT could make), devised a counter against THOSE combos, and repeated the process as it would potentially go on for the next few moves. The difference in that new approach is that it can look at all LIKELY combos for the next 10 to 15 turns, compared to exploring "all" options that would fill in the memory at only 4 or 5 moves ahead (at best) - not enough to beat a chess master. It took a few more seconds per move in order to make all the computations that determine how likely a move is, but since time per turn isn't exactly a requirement in chess, the sacrifice was more than worth it. With all that said, the point is valid regardless. Yes, AI tends to be good, if not better, than humans, but only at a specific narrow task that has clear rules defined.

If the human brain were so simple we could understand it, we would be so simple, we couldn't.

OMG. For all these years I've misunderstood the fruit fly joke. I'm glad I wasn't in charge of talking to any AIs.

man there is a way Brailsford talks that just captures me ...... couldn't stop watching

Thumbs up from Hungary! I love this channel, helped me a lot in my studies in HighSchool, very interesting topics. I will be applying to Cambridge next year, but I am seriously considering Nottingham as well, just because of the 60 Symbols and Computerphile channels. A school with such knowledgeable and energetic professors can't be a bad place anyhow :) Do you have any Hungarian relations, or just picked the language for it's different pronounciation?

I would ask a computer what it itself would ask another computer during a Turing test

Love this guy :) So energetic!

Another excellent video!

Watching this in 2023 and paused it to ask ChatGPT the difference between "time flies like an arrow" and "fruit flies like a banana" and it instantly gave me a far better analysis of the difference than I would have been capable of. Vorsprung durch technik, folks. We let the genie out of the bottle.

Exactly sir! Excellent answer!

analyze the difference between "time flies like an arrow" and "fruit flies like a banana"\ "Time flies like an arrow" and "fruit flies like a banana" are two different phrases that use a similar structure but have completely different meanings. "Time flies like an arrow" is a metaphor that suggests that time moves quickly, just like an arrow moves fast through the air. The phrase is often used to emphasize that time passes by quickly and that we should use it wisely. On the other hand, "fruit flies like a banana" is a play on words that uses the same structure but has a completely different meaning. This phrase is a humorous statement that pokes fun at the common fruit fly. It suggests that fruit flies are attracted to bananas, which is a well-known fact, and that they move quickly, just like time. In summary, "time flies like an arrow" is a serious metaphor that emphasizes the fleeting nature of time, while "fruit flies like a banana" is a humorous statement that plays on the similarity in structure between the two phrases to make a joke about fruit flies. - ChatGPT 3.5 Mar 23 Version

the last few minutes of this made me laugh way more than it should have.

This was amazing and interesting!

the new google Alpha zero engine works a bit differently than typical chess engines. It constantly plays games against itself and learns form the moves it makes. I assume it also uses a degree of brute force calculation aswell. When it played at an engine tournament I don't think it lost a single game, half wins, and half draws.

Simply fascinating.

LOLz, looking at the"recent" comments it might be time to revisit this interview with Professor Brailsford. He's always been my favourite and I'd really like to hear this commentary on more recent developments, even if they are not "trendy" ;-) Plz; I apologies if I sound like a teenager, but I have to say, I really like the way he brings things back down to Earth. PS, I wrote that last sentence before realising I was reflecting Prof Brailsford; thumbs up computerphile for influencing not only thinking but apparently language :-)

Me: Can you analyze the difference between "time flies like an arrow" and "fruit flies like a banana"? ChatGPT: Certainly! "Time flies like an arrow" is a proverb that means time passes quickly. It is often used to express the idea that time seems to pass more quickly as one gets older. "Fruit flies like a banana" is a statement about the behavior of fruit flies, which are small insects that are attracted to overripe or rotting fruit. The statement means that fruit flies are often found near bananas, as they are attracted to the scent of the fruit. The main difference between the two phrases is that "time flies like an arrow" is a proverb that uses the metaphor of time passing quickly to express a common observation about the passage of time. In contrast, "fruit flies like a banana" is a factual statement about the behavior of a particular type of insect.

The definition of intelligence changes every day, it will always be "50 years in the future" Because our expectation of the future moves up as our current technology does.

Isn't there a bronze silver and gold Turing prize. I'm pretty sure I could prove myself as human in the test.

probably the greatest explanation of my life

Much better than your last video about AI but it would be nice to hear some expert ( Geoffrey Hinton, Andrew Ng, ...) on the field of deeplearning and what he says about the future of AI and how the current best techniques work. But I know it might be a bit hard to get them...^^

It's interesting to note that Turing's formulation was 'Could you tell whether the entity at the other end of the teletype was male or female?' which would have been a natural topic at about 6 minutes in when we get to the subtleties of communication... but that would bring us uncomfortable close to Turing's own actual scandal. (And yay! Cumberbatch, etc...) 'Disambiguation' is such a lovely word! But when you experience it, it's so Zen, isn't it? - that sudden flash of insight... When you realize the meaning of Groucho Marx's joke, "Time flies like an arrow; fruit flies like a banana"...

Ok, I'm no expert ether but it's my understanding that computers and organic brains work in very different ways. As I understand it a neuron is much more complicated than the mass of tiny switches that make up a CPU.

AFAIK, Deep Blue did use pattern-matching. Yes, very complex one, but I'm sure I've heard that it's knowledge base was built on a lot of logged and analysed chess games.

I'd really love to hear more about the subject of artificial intelligence by Professor Brailsford. I think, if the machines and the AI programs just get complex enough by becoming powerful enough (in calculations per time), so they can closely approximate the human ambiguity, while being programmed with the knowledge about the world, it should be possible to create something that talks and responds almost like a human being. Of course, like with the travelling salesman problem, there will be this 5% of error margin, but I think that is also something which can be reduced to "good enough" by other clever algorithms for pattern recognition. There is so much in the human mind that works based on pattern recognition, and if we have machines with enough layers of pattern recognition connected to the actual "processing engine", it will be possible to closely approximate a human being. Maybe nowadays, we still need the power of several mainframes for that, so it is still impractical, but as always, technology progresses and will provide more computational power on less space and energy consumption. So, in order to fool an average human being, it would not be necessary to understand any quantum effects in the brain that are possibly there (or maybe not). In the end, I think, we may even find out that there cannot be something like a perfectly conclusive Turing test (if that isn't an accepted fact already). Professor Brailsford, please talk more about this subject!

The WHY motivations to portions of the conversation can quickly lead to a background not existing.

Interestingly, chatGPT replies to the say something in another language question like "To translate a phrase or sentence into Hungarian, you can use a translation tool such as Google Translate or consult a Hungarian-English dictionary."

I recall reading somewhere that there was a Turing Test for game AI, and some neural-network-based bot managed to fool the testers into thinking they were playing against a human opponent.

well fruit *would* fly pretty similar to bananas, just saying haha

5:55 I lost it. Haha

I think one thing that is kind of overlooked about the turing test by most is that you probably would have to repeatedly give it. Because humans adapt, and learn, and change. We may not perceive something as what it is until we know what signs to look for. Perhaps, say, we make a machine and it passes the test for a reasonable sample size of people. Then a few years later it fails miserably because people have figured out the quirks. I don't think one test is enough. You'd need not just an A.I. that could fool people today, but one that could continue to evolve to fool people forever. But at that point, it's frightening to think what that could mean.

So even incredibly intelligent people like Roger Penrose fall prey to the quantum-physics-equals-magic fallacy.

My prompt: Hi ChatGPT-4 I got a riddle for you: "Analyze the difference between time flies like an arrow and fruit flies like a banana." ChatGPT-4 Response: This is a classic example of a linguistic ambiguity, often used to illustrate the complexity of language understanding. The sentence "Time flies like an arrow; fruit flies like a banana" is a humorous play on words that relies on the multiple meanings of the words "flies" and "like". 1. "Time flies like an arrow": In this sentence, "flies" is used as a verb, and "like" is used as a preposition to indicate similarity. The phrase is a metaphor suggesting that time moves swiftly and directly, similar to how an arrow flies. 2. "Fruit flies like a banana": Here, the sentence structure is the same, but the meanings of "flies" and "like" have changed. "Fruit flies" is now a noun referring to a type of small insect, and "like" is a verb meaning "is fond of". So, the sentence is saying that fruit flies are fond of bananas. The riddle is amusing because it uses the same sentence structure to express two completely different ideas, playing on the different meanings of the words.

I enjoyed the time flies example

Chat 3.4 response to (Analyse the difference between, time files like an arrow and fruit flies like a banana): The phrases "Time flies like an arrow" and "Fruit flies like a banana" are examples of linguistic devices known as puns or wordplay. They play with the multiple meanings of words or phrases to create humorous or thought-provoking statements. Let's analyze the difference between these two phrases: "Time flies like an arrow": This phrase utilizes a metaphor, comparing the passage of time to the flight of a fly or an arrow. It implies that time moves swiftly, just as a fly or an arrow quickly travels through the air. The phrase also suggests that time should be valued and used efficiently, as it can be easily lost or wasted. The pun lies in the wordplay between "flies" (referring to the insects) and "flies" (indicating movement through the air). "Fruit flies like a banana": This phrase also involves a pun, but with a different context. Here, the wordplay is based on the multiple meanings of the term "fruit flies." On one hand, "fruit flies" refers to small insects that are attracted to ripe or decaying fruits. On the other hand, it can be interpreted as "fruit flies" being the action of fruit (as in fruits moving) in a manner similar to how a banana, a type of fruit, might move or be thrown. The phrase cleverly combines these two meanings, creating a humorous effect. In summary, the main difference between the two phrases lies in the objects being compared and the wordplay being used. "Time flies like an arrow" focuses on the metaphorical concept of time passing quickly, drawing a parallel between time and the swift flight of a fly or an arrow. On the other hand, "Fruit flies like a banana" utilizes a play on words involving the multiple meanings of "fruit flies," combining the insect with the action of fruit, specifically a banana. Both phrases demonstrate the creative use of language to evoke amusement or provoke thought.

I think this is really missing the point of what the Turing test is about. The test was Turings answer to the question of whether a machine could ever be said to be truly intelligent. His idea was that the only way you can measure a concept like intelligence is through its performance. You cant look inside the box and find intelligence by analysing its parts, you just have to accept that if every way you look at it it looks smart, you might as well call it smart. Even if one brain is made of spongy tissue and one is made of c++, if they can do the same thing, they are equally intelligent. The conversation test was just an example.

Could you post an URL to the book by Roger Penrose that Professor Brailsford is talking about?

I've considered the thought before that our brains harness some quantum mechanical properties. But then I observed that thought and it quickly disintegrated... Bad jokes aside, I truly have considered the thought, but I'm no neuroscientist nor a theoretical physicist, so I have no quantifiable education in the matter. But from what I've learned reading various scholarly articles and watching various educational videos on youtube, it doesn't seem completely unlikely that our brains might make use of some quantum mechanical properties. Take for instance our lightening-quick ability to process sound waves, solo out speech, grammatically analyze said speech, and then - the thing computers have yet to even come close to doing - understand those words. That is, as the Professor touched on, we are taking those words, the sentence structure, along with other various clues such as body language, and we put all of that information into context, or we apply it to everything that's going on around us. (For instance, someone mentions a plane crash. Immediately we think, "Was there a plane crash in the news?" "Was there a movie that recently came out about a plane crash?" etc.) Finally, after subconsciously coming up with this list of possible meanings for the airwaves that just graced our eardrums, we subconsciously pick the one that makes the most sense. There is so much more than simple pattern recognition going on that I don't think computers will ever be able to become 100% indistinguishable from humans. Until someone makes a computer that is capable of keeping track of current events, understanding abstract speech like similes and metaphors, that can perceive and make sense of nonverbal cues like body language, can correctly analyze mood and meaning based on tonal differences, and is capable of complex analysis of n-dimensional space in regard to context - and all that in the matter of milliseconds - I refuse to believe that computers will ever become indistinguishable from humans. Finally, to bring it all back to quantum mechanics, it would make sense if the reason we are capable of such incredibly complex analysis is by means of quantum mechanics. Needless to say, the human mind is not just a complex Turing machine.

can there be something on this channel like calculator unboxing for numberophile? perhaps software/app 1st use?

time flies like an arrow vs. fruit flies like a banana ... love it

It seems, at least on the surface, like the process Roger Penrose used to arrive at the conclusion that "consciousness has something to do with quantum mechanics" is "consciousness is mysterious, quantum mechanics is mysterious, therefore they are related."

I'm not sure if would be considered quantum effects, but neurotransmitters aren't shot out across synapses like a photon torpedo. Once they are 'let go' (broken chemical bond?) by one neuron, Brownian motion takes over and some distribution of the neurotransmitters reach the other brain cell. Certainly random. Am I wrong?

What does Professor Brailsford think about the I.B.M. Watson computer? A device that does I think does a good job of analyzing context and parsing language. It may not be turing test perfect, in fact instead of the random answers that chatbots give it may be too specific and too correct at some points

One of the most difficult things to consider when thinking about a computer that can match a human mind is that the human mind holds outrageous amounts of data. Not just conscious memory but also subconscious and active analysis. I would think, to make a computer that sophisticated we would have to play on the advantage of computers being ageless rather than their efficiency. Why not start with instinct, and move from there. Go into associations, after all that unless we discover that nature vs nurture simply does not exists, we might have to hard code preferences to mimic human behavior.

Yeah, every time I read a new article about how we keep getting closer to real AI, I always think the same thing. Just because computers keep getting faster doesn't mean they are any closer to getting smarter. As the Professor noted, they are great at brute-forcing their way through certain tasks. But it's the software that will make them true AI, and I can't say that I am certain that humans are smart enough to write such code.

Can we get the professor's opinion on IBM's Watson and Jeopardy?

I would love to know what he would think about this topic right now ...

my favourite quote : 7:16 "Ok, artificial intelligence program... analyse the difference between 'time flies like an arrow' and 'fruit flies like a banana'..." - Proffessor Brailsford

will be sing this video for my AI class thanks!

I'm interested in the turing test for chess. Determine if a chess player is computer by analyzing a finished game. It's important for detecting cheaters.

CharGPT3.5 on “Analyze the difference between ‘Time flies like an arrow’ and ‘Fruit flies like a banana:” “The difference lies in the interpretation of the phrases: 1. ‘Time flies like an arrow’ suggests that time passes quickly and consistently, akin to the swift movement of an arrow. 2. ‘Fruit flies like a banana’ is a play on words, where ‘fruit flies’ refers to the insect, and the sentence humorously suggests that fruit flies have a preference for bananas, which is both literal and figurative.” Perhaps that “10 years” figure wasn’t too optimistic after all!

i was really confused by "fruit flies like a banana" - dammit i'm a robot!

Good thing computers speak in series of clearly distinguishable energy levels, not in terrible puns that only work in a language composed of what seems like 95 % homophones ...

This guy gets it

Deep Blue had the benefit of analysing all Kasparov's matches with the back up of computer programmers and chess experts . Kasparov was facing an opponent on his own basically. It was a narrow victory for the Deep Blue in the end

In Turing's time, it was thought that if anyone ever could program a computer to beat a Grand Master in chess, then it would be intellegent. Then we did it and immediatly everyone said, well THAT isn't REAL intellegence. But, if we could program a computer to play Go... Then we did that. So, they said, if we could translate natural language. Ah, Google translate? Whoops.

The Turing Test really was a child of it's age. The 1950's were the heyday of behaviorism -- a school of psychology that only looks at behavior, and dismisses all talk of feelings, thoughts, and other "internal" states as unscientific. From that view, the question about whether the computer *understands* what you're typing is unimportant or simply meaningless -- to everyone before and after, it's crucial to whether or not we'd consider this kind of AI to be possible. Also, look up "Chinese Room" on wikipedia to read more about this debate.

It seems very likely that the source of self and consciousness will be found to be quantum.

Even if quantum effects are involved, you can set every possible wave-function to a different state in a Turing machine. The wave-function is continuous, but you can divide it up into pixels, and make those minute enough that any quantum effects are irrelevant. However, while you could theoretically simulate a human brain like this, it would be far too inefficient for even the best computers. Then again, if moors law continues, we might be able to run such a simulation in a million billion billion billion years. (assuming 4 picometer cells, a 1liter brain and 64 levels of probability that an electron is in a cell)

you should see the classified stuff they did in the 1970s with a.i.

My phone picked up that "Okay Google".

here is a question I would like brady to ask mathematicians, scientists and computer scientists: what is their opinion on brute forcing to achieve a solution? the rubiks cube "god number" which was found to be 20 was not solved via a mathematical solution. mathematics narrowed down the number of puzzles that required solving but huge computational power was used to brute force the answer that was 20. Is this answer satisfying to a mathematician or computer scientist knowing that brute force was used to prove a problem like this?

Can you have a turing test to find out if you're playing against a human or a robot at chess?

The problems of subtlety, metaphor, and common usage will be the ones that prevent strong A.I. from being realized. Unless you can create a program that can learn, experience, remember, synthesize, generate and understand abstractions, you can never artificially construct consciousness.

Computers will never become as fast as the mind until the way a computer processes information is not through the software changing, but instead through the hardware changing. Digital may be efficient and simple, but it doesn't, and will never, take into account the incredibly complexity and amount of information that can fit into a tiny space.

Do one about IMB's Watson (extrabits).

When he said fruit flies like a banana I thought about a banal flying like fruit. Probably because fruit fly in not too standard a word for me in everyday use. So no, I don't see why computers are so different to our brains.

You: What is your name AI: John You: That is my name also! What is my name? AI...

At 6:48 my Google Home said "I don't speak that language yet."

Fruit flies like a banana I chortled on all levels

Haha, I have Roger Penrose's Emperor's New Mind sitting right here on my desk.

Ah, I see the Kubrick reference :-)

... Apparently I am a computer, I understood those two sentences like a computer would

he beat him along time ago not beat him off along time ago

YES!!!!!! I've been waiting for this. With all the Turing talk I figured it was inevitable eventually. :)

***** Could you please do a video on esoteric programming languages?

The turing test? More like the enduring test

What would we do next when the perfect A.I., which can and will imitate a human completely, emerges?

ChatGPT sends its regards

If you want to know more about Deep Blue watch "Game Over:Kasparov and the machine" here on YT.

It is so interesting that it seems the human brain isn't processing linearly but everyone assumes it is

And here we are with gpt 4

Me: hello, define the difference between these 2 sentences. 1. Time flies like an arrow 2. Fruit flies like a banana. ChatGPT: The first sentence, "Time flies like an arrow," is a metaphor that compares the passage of time to the motion of an arrow. The second sentence, "Fruit flies like a banana," is a statement about the behavior of a type of insect known as fruit flies, which are attracted to ripe bananas and other fruits. In this sentence, "like" is being used in the sense of "enjoy" or "prefer," rather than as a comparison.

Imma say my Pops, almost 70, said AI needed artificial stupidity to be complete.

What about artificial neural networks? They're incredibly good at learning and they're more generalized, also the brain is largely an incredibly deep neural network. Could artificial neural networks be the key to making a more human-like artificial intelligence?

I'm reading "The Emperor's New Mind" right now. XD

4 people wear a helmet. 4 people wear a piano. ... How many buckets do you have? :D

So, the machine performed the Divine Move from Go, but in chess?

So I guess we're going have to wait for quantum computers to see if a machine can be ironic or sarcastic...

What happened to Brady...?

Can there be anything more human than the Turing test? If you can fool a human you must be equivalent to a human. It boils the qualifications down to the bare minimum, deception.

I wish I could adopt this man as a third grandpa

Google Translator pronunced the word well :D