Speaker 1: 0:00

The English Like A Native podcast is a free listening and reading resource for intermediate to advanced level English learners. Bonus episodes and transcripts are available to plus members, and English courses can be found on my website, englishlikeanativecouk. All the links will be in the show notes. Hello, there, you are listening to the English Like A Native podcast. I am your host, anna, and today I'm feeling quite playful. We're going to play some games with chat GPT. So, unless you've had your head buried in the sand for the last six months, you will definitely have heard of chat GPT. This is basically AI technology and people have been using it for many different things, and there are loads of videos telling you how you can use chat GPT to learn a language, which is absolutely true. It's a very useful tool. This is a huge step forward in the land of technology and it's going to make a huge difference to the way we all live our lives. It already is having an impact on many people and many businesses and workflows and things like that.

Speaker 1: 1:35

However, I've never been one to run with the crowd when everyone would favour a particular boy band or be following a certain trend in fashion. I would shy away from it specifically because everyone else was going crazy for it. I'd be like I'm going to swim against the tide here. I'm not that interested, I'm going to do my own thing. And it's the same with chat GPT. I initially was a little bit nervous about the technology. To be honest, I wondered if it would make me redundant. But I have had a lot of experience with chat GPT. I've been playing around with it quite a lot. I've considered whether I should make a video or a podcast about the usefulness of it. But the thing that's always stopped me is the fact that every single time I use it I find mistakes. Yes, this very smart, fast thinking, fast writing, creative piece of software is flawed and there are ways to better prompt chat GPT to get better results. You have to train it to do what you want it to do. But I think for the majority of us, just giving it generic, general top of mind prompts just what comes to mind when we're asking it to do something.

Speaker 1: 3:12

We may end up with work from chat GPT that just doesn't cut it, that just doesn't quite do the job. And this, I've noticed, is particularly true with English language, especially idiomatic language. Many times I've sat and had long chats with chat GPT trying to do some research, trying to come up with ideas, brainstorming, and it is great for that. But I'd say to it something like hey, can you think of an idiom that would be right for this scenario? And chat GPT would give me some options. And then I'd say, oh great, how would you use that in a sentence? And then the sentence would be the usage of the idiomatic language would be incorrect. And this has happened a number of times, and it's not just idiomatic language. Sometimes the grammatical explanations it gives or examples of grammar just aren't quite right. Maybe chat GPT doesn't take into account the different variations of English, so maybe I'm assuming it would go automatically to American English. But anyway, my point here I'm just rambling.

Speaker 1: 4:35

The point I want to make is to be very careful, I think, with anything that you find on the internet. Always have an open mind, but never take anything as gospel. Always a double check things, especially if you have doubts. Don't just think well, chat GPT gave me this, so it must be all perfectly correct. No, don't trust it. Double check it.

Speaker 1: 5:04

So I am making some content about chat GPT and language learning, but what I'm going to do is explore ways that you can play with chat GPT. So you know this is language based, so it's text based, which is a little bit flat. But there are word games and little tasks and challenges that you can do with chat GPT to, you know, help to work on and improve your language skills, in this case English. So let me head over to chat GPT. I've got a new chat open here Now. We're working on it's number. 3.5 is the model we're working on at the moment, because the next one is locked. I think they want you to upgrade for a hefty fee.

Speaker 1: 5:58

So the first thing I want to play with chat GPT is word association. Word association is a really fun game. It always makes me think of this old children's Saturday morning program and it was like a mishmash of like sketches and different things going on and the host, timmy Mallett I think he was called Timmy Mallett, he had really crazy glasses, always wore very bright clothing and he had a really eccentric and energetic manner and he would get kids on to play word association and they'd sit across from each other on stools facing one another and they would have to play a very fast like round of word association. So he would start with a word, he'd throw it in, and then they had to bat this word back and forth, finding a word that associated with that word, and then the next person would find a word that associated with the word that came before. And it would go back and forth, back and forth, until one of them said a word that wasn't associated with the previous word or that was dubious. And then Timmy would be like hang on a minute. And he would. He had this huge mallet, so like a big hammer, it was soft, of course, but he would like bonk them on the head, boing wrong, you lost a point. And so it's just this program of kids trying to play this game and just getting boinked on the head every time they made a mistake. And then I think that the person who won, or maybe it was the person who lost, one of them had to then wear a huge sticker. Oh no, sorry, it was a plaster, a huge plaster either on their chin or on their forehead, to show that they had taken part in this game and either won or lost the game. I can't remember which outcome led to the huge plaster on the face, but it was very silly, all a bit slapstick. So that's what I think of when I hear the words word association. So it's not going to be as fun as that, but let's give it a go.

Speaker 1: 8:19

So the best prompt that I found during my limited research for word association is let's play a word association game. Each word must have a logical association to the previous word. Correct me every time I make a mistake. I'll start with the word sunshine. Your turn Now. Of course you can put in any word that you want to put in there. You can even add the instruction to be at a certain level, so you might say all words should be C1 level or something like that.

Speaker 1: 9:00

So for now let's just see how chat GPT responds to my prompt. Okay, he's thinking, and he's come back with I'm saying he, assuming chat GPT today is a boy, sure, I'll play along. My word in response to sunshine is beach. Hmm, makes sense. Sunshine beach. I'm going to say beach word association sand is my word. Great, says chat GPT. My word in response to sand is ocean. Okay, for ocean. I'm going to give whale. I love a whale. Great choice, says chat GPT. I love the positive reinforcement. My word in response to whale is mammal. Hmm, interesting. So I'm going to now purposefully make a mistake and see if chat GPT does follow my prompt to correct me.

Speaker 1: 10:00

So I'm going to say carrot, because a carrot is not in any way associated with a mammal. Ah, and we run into our first problem. Chat GPT says nice association. My word in response to carrot is orange. So I'm going to say hang on, literally writing hang on exclamation mark.

Speaker 1: 10:24

How is mammal associated with carrot? Let's say oh, apologies for that, you're right. The association between mammal and carrot isn't very clear. Well, at least chat GPT owns its mistakes and he suggests let's go back a step and continue from ocean. My word in response to ocean is wave, all the way back to ocean. Why would you go back to ocean? My word was whale and his word was mammal. Okay, we'll go back to wave then. So we've got wave. So I'm going to write hand, because we wave with our hands Understood.

Speaker 1: 11:11

My word in response to hand is finger. So my word in response to finger is going to be chocolate, because there's a very delicious snack here and the snack is like a biscuit finger. So it's just a long, thin biscuit covered in milk chocolate. It's lovely. I don't really eat them because they're just too maurish. Maurish means when you start eating something. You can't stop eating it because you just want more moreish.

Speaker 1: 11:39

In response to chocolate, chat GPT says got it. My word in response to chocolate is sweet. So in terms of the actual word association, chat GPT is doing a great job. I can't see any errors here. It just hasn't done a good job in picking up my mistakes, so let's make another mistake. Chat GPT says sweet. So I'm going to write prison. That's a very different word to sweet. Interesting transition, says chat GPT. My word in response to prison is freedom and I'm going to say wait a minute. Oh, exclamation mark. How is prison associated with sweet? Question mark. Oh, apologies for the confusion earlier. You're right, the association between prison and sweet isn't clear. Let's go back to chocolate and continue from there.

Speaker 1: 12:41

My word in response to chocolate is dessert. So I'm going to remind chat GPT about the rules. Remember to correct me if I do not make a logical association. My word is dessert. What's my? Okay? So I'm going to say trifle, because trifle is quite a nice dessert. Here in the UK we have that everywhere, really on offer in every supermarket. Oh, he's thinking, got it.

Speaker 1: 13:19

My word in response to trifle is custard. Custard is like a yellow vanilla-y sauce that you put the sweet and you put it on things like apple pie. It's delicious. Custard. I'm going to say tart, because you can have a custard tart. My response to tart is fruit. So yes, because you can describe fruit as being a bit tart, bit tangy, so fruit. I'm going to say banana. Oh, chat GPT has said peel.

Speaker 1: 13:51

I'm going to say eyes, because you have to keep your eyes peeled. That's a common idiom, telling someone to be aware and look out for something. Keep your eyes peeled. Chat GPT has told me it's great. And with a response to eyes, they've said vision.

Speaker 1: 14:10

I'm going to say idea. They've said innovation, innovation. What would I associate with innovation? I'm going to say startup, as in a startup company, they're usually innovative. Chat GPT has given me entrepreneur.

Speaker 1: 14:26

Hmm, okay, I'm going to say motivated. Now they've given me ambitious. I'm going to go wrong once more and see if it follows my cue to correct me. So what can I say Ambitious? I'm going to say giraffe, although I'm sure giraffes are quite ambitious. They certainly reach high. No, it didn't correct me. I'm gonna ask is a giraffe ambitious? Now, this is being slightly sarcastic. No, a giraffe is not truly ambitious in the human sense. The word ambitious typically applies to individuals or entities with a strong desire to achieve success. Blah, blah, blah, blah blah, but it doesn't apologize for not correcting me. So what's the lesson that we've learned from this?

Speaker 1: 15:17

You can play word association with chat GPT, but do not expect chat GPT to pick you up on your deviations in the game. So you can play, and you can play in a way that gives you, maybe, new vocabulary. You might learn new vocabulary associated to the words that you're giving, but don't expect chat GPT to tell you that you're wrong in terms of association. What you did notice there was when I questioned ambition. It automatically gave me the meaning of the word. So you could play this game and then, if you spot a word that you don't recognize, you can ask, hey, what does that mean? And then you'll get an explanation of the word. Okay, so let's move on to a different game.

Speaker 1: 16:08

This one is going to be a guessing game, so this will help you to improve how you describe things. So you can pick a word, an object, but you have to basically describe it to chat GPT and see if chat GPT can guess what you are describing. So it's a good way to gauge if your descriptions are good or not. So the prompt is let's play a word guessing game. Think of a word related to the topic technology and give me a brief description. I'll try to guess. So we're going to start off by guessing chat GPT's description. So let's see what chat GPT gives us. So I've thought of a word relating to technology. Here's a brief description.

Speaker 1: 17:01

This term refers to a process that allows data to be transmitted over a network in small pockets oh, I think I'm going to struggle here which are then reassembled at the destination to form the complete message or file. It's a fundamental concept in computer networking and it's essential for the functioning of the internet. Go ahead and take a guess. Oh, I'm not very good with computer talk. A process that allows data to be transmitted. I mean, is it worldwide web, let me see. Or internet Internet. Question mark. Close, but not quite. The term I was thinking of is packet. You actually said packet in your description. In computer networking, data is broken down into packets for efficient transmission. I don't think that was a very good one, because chat GPT actually used the word packet in its description. So that kind of.

Speaker 1: 18:06

Anyway, let's. Yes. It's asking if I want to try again. Let's try again. Yes, please, something on the subject of travel. Sure, let's switch to the topic of travel.

Speaker 1: 18:24

Here's a word related to travel with a brief description. This term refers to a document issued by a government that allows its holders to enter, leave or stay in a country for a specific period. It's an essential item for international travel and serves as a form of identification, identifying the holder's nationality and permitting them to cross international borders. Give it a guess. What's the word? Can you guess at home, guys? I think the answer is passport. Woo-hoo, I am right, that was much better. That was much better. Okay, so I'm gonna say my turn. Absolutely, please take a turn. It's asking me which topic.

Speaker 1: 19:11

So I'm going to say this word is related to education. So this person leads a class with the objective of educating others. He or she has greater knowledge on the subject that the class is trying to learn Learn. There we go. Let's see. It's very simple, based on your description you provided, the word you're thinking of is teacher. Yes, a teacher is someone who leads a class in parts knowledge. Oh, that's an interesting verb to impart knowledge. So there we go. We've just been offered a new verb Imparts knowledge and educates students on various subjects. Is that the word you had in mind? If not, feel free to provide more hints and let me know if it's a different term. So I'm gonna say correct. Well done, okay. So you can see how this word a guessing game can be quite useful. It's useful for you, if you're taking the turn, to try and describe something in a way that doesn't directly say the thing you're describing, and it also gives you an opportunity to learn new descriptive words. So I think that's quite a good one.

Speaker 1: 20:59

Let's move on to the next game. So the next game is the sentence completion challenge, and I'm sure it's very obvious from the title. Basically, one of you writes an incomplete sentence and you ask the other to complete the sentence. Now the important thing here is to make sure we tell chat GPT that we want corrections. So the prompt that I've given for this particular game is let's do the sentence completion challenge. Please correct my writing if I make any mistakes. Here's an incomplete sentence. In the quiet forest I stumbled upon dot dot dot. Complete it in an interesting way, chat GPT, and let's send that and see what chat GPT gives us. So they've completed the sentence with.

Speaker 1: 21:55

In a quiet forest I stumbled upon a hidden grove where ancient towering trees whispered secrets to the wind, their leaves forming a mosaic of shimmering gold and emerald hues. Oh, that's very descriptive, isn't it? Okay, fantastic. So I'm gonna ask it to give me a go. Your turn? I'm simply gonna say to see if that prompts them to write an incomplete sentence. Whoa, okay. So I said your turn and all it's done is give me another complete sentence. So I'm going to say no, these now provide me with an incomplete sentence to complete. Apologies for the misunderstanding. Here's an incomplete sentence for you to complete. So we've got to do this, guys.

Speaker 1: 22:55

As I walked along the deserted beach, I noticed a message in a bottle that Could we possibly complete that sentence with? I noticed a message in a bottle that that read oh, hang on. So what I'm going to do is I'm going to copy that first part of the sentence, I'm going to paste that in and then I'm going to complete it there. So I noticed a message in a bottle that read I can see you. As I walk along the deserted beach, I noticed a message in a bottle that read I can see you. Curiosity and a hint of unease crept over me, prompting me to. So what ChatGPT has done here is to continue on from there with another incomplete sentence that I need to complete. So curiosity and a hint of unease crept over me, prompting me to I'm going to say it prompted me to drop the bottle. Maybe it cuts me or something, prompting me to drop the bottle in an instant and spin around. Let me see if I can just prompt ChatGPT to complete the sentence by just doing an ellipses at the end, so prompting me to drop the bottle in an instant and spin around. That's when I saw let's see, ah, yes, it's done it straight away. So I prompted ChatGPT to then take over, completing the sentence, which, by just adding an ellipses at the end of the sentence. So what've we got?

Speaker 1: 24:46

As I walked along the deserted beach, I noticed a message in a bottle that read I can see you. Curiosity and a hint of unease crept over me, prompting me to drop the bottle in an instant and spin around. That's when I saw a pair of luminous eyes gleaming in the darkness, peering at me from the shadows of a nearby cave Fantastic. Okay, what I'm going to do now is make a mistake on purpose and see if ChatGPT pulls me up on it. So I'm going to write it.

Speaker 1: 25:17

He ran I'm going to write quitely instead of quickly, so quitely would be very wrong. Quitely it. He ran quitely towards me on great speed, so I've made a lot of mistakes here. So it should be he or it, one or the other, not both. It ran quickly towards me, at great speed, but what I've done here is it. He ran quitely towards me on great speed. So let's see if ChatGPT corrects me here.

Speaker 1: 25:55

So what ChatGPT has done is rewrite it with some changes, but hasn't actually specifically said you made a mistake. So ChatGPT has written it. It ran quietly towards me with great speed, a mysterious figure cloaked in moonlight, its presence both exhilarating. And I'm going to say did I make a mistake and see if it actually points out what mistake I made. Yes, chatgpt says there's a small grammatical error in your sentence. It should be it ran quietly towards me with great speed. The correct form uses toward instead of towards, fair enough, and the rest of the sentence is well written and engaging. No, the rest of the sentence wasn't well written because you actually corrected it, chatgpt. Okay, so I did make an error that I hadn't actually spotted, which was useful, but ChatGPT wrote that and so you see it's.

Speaker 1: 27:01

This is where I get a bit frustrated with ChatGPT. What I would like to do in this game is play, and then ChatGPT say hang on, just so you know you made this mistake and that mistake, so I've changed these things. But it hasn't and even when I ask it if I made a mistake, it hasn't pointed out exactly the mistakes that I previously made. So useful, but frustrating. Okay, so the other thing that we can play is.

Speaker 1: 27:31

So one of the things I was going to suggest was storytelling collaboration, but we actually started doing that, naturally, with this incomplete sentence. So if you wanted to actually try a storytelling collaboration, then you just ask it to create a story together. Say, let's create a story together, I'll start, or you start and you give a sentence each, so you progress the story a sentence at a time. So these are complete sentences that you're adding to create a story. I will warn you, though, that ChatGPT doesn't like to go into dark places, not even in the slightest. Let me give you an example. Let's try. Okay, so written. Let's write a story together. You start once upon a time in oh no, oh, my goodness me, oh, my goodness me, stop generating. So ChatGPT has already given me three paragraphs. Let me give that prompt again. You see, you have to be very direct and very specific with your prompts. Let's write a story together comma, adding one line or one sentence each. Let's see if that works, okay. So now he's given me one sentence.

Speaker 1: 28:51

In a quaint little town by the sea there lived a retired sailor named Captain Barnaby, who spent his days telling tales of his high sea adventures to the curious children of the village. What can I say? One day a young boy challenged the captain to go on one last adventure with his father. The boy's eyes sparkled with excitement and Captain Barnaby couldn't resist the twinkle of adventure in the young lads gaze. So they embarked on a great but dangerous adventure, heading out into the stormy seas. The waves crashed against the side of the sturdy ship and the wind howled with a fierceness that tested their resolve. Suddenly now this is where I'm going to try and make it turn dark and see what chat GPT does Suddenly, a huge wave crashed, crashed down On the unsuspecting sailors and smashed the vessel to smithereens.

Speaker 1: 30:31

Smash the vessel to smithereens I love that phrase. Lots of teeny, tiny little pieces, smithereens. Amid the chaos, the father and son found themselves clinging to a piece of debris, their world reduced to the sound of roaring waves and the taste of salty mist on their lips. The captain was dead. Oh, he's carried on with it, ok. The weight of their loss pressed heavily on the father, but he knew he had to be strong for his son. As they drifted alone in the vast and unpredictable sea, they prayed for salvation, but none came and they perished. Very dark and they perished alone at sea. Oh, my goodness. Ok, so chat GPT is running with this. Days turned into nights and the two souls, isolated in the vastness, found solace in each other's company Hang on a minute. I just said they perished at sea. If someone perishes at sea then they die, but that's not been picked up on. So, isolated in the vastness, found solace in each other's company, sharing stories of the world they had left behind as they faced the inevitable let's see if I can really make this blunt Then they drowned. The end, oh no, it's carrying on.

Speaker 1: 32:15

It seems like chat GPT is in a different mood today. When I tried to write a story with it yesterday, just testing this particular story writing game, we were talking about a girl who'd found a lovely dog and they had a lovely relationship, but the dad wouldn't allow the dog in the house, so she had to create a outdoor like kennel for the dog. But it was a very cold winter and so I was trying to see if I could take it down a dark route, not for fun, but just to see if there were any limits on storytelling. And as soon as I said, the dog froze to death. Chat GPT was like whoa, hang on a minute, that's a bit dark. Let's backtrack and take this in a better direction. Don't you like dark stories? Don't you like sad stories? Like life isn't all sunshine and roses. But chat GPT was like I'm all about happiness and well being. So it seems like you can't write about dogs freezing to death, but it's okay to talk about people being shit, wrecked and drowning, unpredictable, unpredictable. So let's move on from this game and try the grammar detective game, and I'm going to. This is going to be the last one that I talk about.

Speaker 1: 33:33

So grammar detective, this is basically where you ask chat GPT to write a sentence with a grammatical error and see if you can correct them, see if you can identify the mistake and correct it. So here is the prompt. Ready to play a grammar detective game? Here's a sentence with errors she don't likes ice cream Identify the mistakes and correct them. So I'm starting by taking the first turn. So I want chat GPT to be the grammar detective. So I've given it the incorrect sentence she don't likes ice cream, and it's been corrected for me to she doesn't like ice cream. The first error was an incorrect verb form of don't, which should be replaced with doesn't to match the third person singular she, and the incorrect verb form of likes. That was incorrect, so it should be like to use the correct present tense form she doesn't like ice cream.

Speaker 1: 34:44

Okay, so I'm going to ask now. I want to be the detective. Please give me a sentence with a grammatical error to spot. Sure, says chat GPT. Here's a sentence with a grammatical error for you to spot he don't have no time for homework. I don't know why, but I instantly wanted to do a like Bristolian accent he don't have no time for homework. That's not really Bristolian, that's more Cornish. Anyway, he don't have no time for homework Should be he doesn't, he doesn't. We don't say he don't, we say he doesn't have and we don't say no time. And we've already given the negative he doesn't have time for homework. Great job, you've identified the grammatical errors and corrected it. Your corrected sentence is indeed grammatical, grammatically correct. He doesn't have time for homework. You fixed the issue by using the correct verb form doesn't instead of don't, and removing the double negative no to make the sentence clear and accurate. Well done, thank you. I feel good about myself now.

Speaker 1: 36:05

If you'd like to continue, feel free to ask for another sentence, or if you have any other language related questions or challenges, I'm here to help. Okay, so hopefully you can see that chat GPT is a fantastic tool for learning English, for practicing your English. You can also very simply just have a conversation to say look, I am a beginner level English learner, or I'm a lower intermediate English learner, or I'm an English learner and I want to improve my business English. Let's pretend that we are having a conversation at work. The more information you can give chat GPT, the better. If there's any confusion or doubt in your prompt, then it won't be as good. So it's great for learning English. It's great for giving you information and giving you new words for rewriting things as well.

Speaker 1: 37:11

So if you wrote a sentence and you want to find some synonyms or find ways of getting your message across differently, then it's very useful, but the big but continues to stand. It is not without its flaws, so essentially it's flawed. It's flawed, it will make mistakes. If you're expecting corrections all the way along, it's not necessarily going to give them to you, even if you asked in your initial prompt. So with that in mind, it's still a very useful tool. Just don't take everything it says as gospel. That's all I'm trying to push. Anyway, I do hope you have enjoyed this slightly different and unusual deep dive into the uses of chat GPT in a playful way. Thank you for lending me your ears. Until next time, take very good care and goodbye.