ChatGPT actually wrote an entire language with a working phonology - including a phonemic inventory and phonotactics, grammar, and a sample lexicon. It even translated a few sentences.
Try to tell it smt like "SolidGoldMagikarp", "PsyNetMessage", " attRot", or "EStreamFrame" XD it derps out and halucinates entire context and starts to talk random bullshit.
I gave it a playlist and asked it for the tempo of each song and it just made a bunch of tempos up, however they were all in somewhat plausible ranges (i.e. electronic tunes tended to stick around 120-130, folk songs were in the 100bpm range, etc.) very strange
The "existential dread" you wrote about is literally what I'm actually afraid of. You described everything perfectly. It sort of feels like, little by little most people will stop trying to figure things out and just ask ChatGPT. Again, one of the things that makes us human is our creativity. Besides, it's just scary to think how many jobs will be replaced by this technology. We still don't know how many, but it's sure it's going to happen. Furthermore, there is also this fear of AI taking over humanity. We don't know exactly how that's going to take place, but I'm pretty sure that even if it doesn't happen like in the sci-fi movies, it's going to happen in one way or another. And the worst part is having no idea how to prepare for it.
So if we just 'crawled under a rock', and refused to use AI, which is already in google assistant and google maps and fb algorithms. But if we didn't use AI for creativity or problem solving, we'd stay 'more human' but probably be way less productive, and maybe culturally lag behind. Idk.
At this point AI is still input and output. Without the input it's nothing - that's why it has trouble talking about unpopular/poorly known/less discussed things. A more likely future is one where much of humanity is contributing to a larger database for the benefit of all.
I wonder if he actually wrote that or if he let it generate with a prompt like: "Write 5 paragraphs from the perspective of a human who feels existential dread about the advancements of AI."
@azuurasmr7937 Yeah, exactly, the thing is that AI is going to become a big part of our lives in the future. Of course, it has advantages, but the disadvantages are going to be huge as well :( especially for the low and middle class, maybe.
It's a learned skill. You can get more creative by exposing yourself to lots of different things from different mediums and genres. Also trying to do things in different ways.
Artificial Consequence Verse 1: In this world of AI, we're caught in a paradox Progress and convenience, but at what cost? Will robots replace our jobs, will we be obsolete? Will they have our knowledge, and outsmart our own beliefs? Chorus: The future's uncertain, when machines hold the key What will it mean for humanity? We must act with caution, and tread carefully To ensure our survival, and our destiny Verse 2: In the age of information, with power at our fingertips Are we willing to sacrifice our freedoms for a few clicks? Do we trust algorithms to make our choices for us? To decide our fate, and what we consider just? Chorus: The future's uncertain, when machines hold the key What will it mean for humanity? We must act with caution, and tread carefully To ensure our survival, and our destiny Verse 3: As we move forward, we must ask ourselves What kind of world do we want to create, what will it entail? Will we let the machines decide, or will we lead the way? Will we prioritize progress, or will we think and say? Chorus: The future's uncertain, when machines hold the key What will it mean for humanity? We must act with caution, and tread carefully To ensure our survival, and our destiny Outro: So let's move forward with eyes wide open, With the courage to make the tough choices, And the humility to recognize our limitations. Let's ensure that AI serves humanity, Not the other way around. Written by ChatGPT v. 3.5
@@shey_clone Are you talking about this one?: "I'm sorry to hear that you're feeling existential dread. It's understandable to feel overwhelmed by the capabilities of AI and the potential implications for humanity. However, it's important to remember that technology is a tool created by humans, and it's up to us to decide how we use it. While AI may have the ability to solve problems in ways that humans cannot, it doesn't necessarily mean that it will replace us. Creativity is a fundamental part of the human experience, and it's unlikely that we will ever be able to fully replicate it with technology. AI may be able to create art, but it will never be able to fully capture the human experience behind it. It's also important to remember that there are many things that humans excel at that AI cannot replicate. Empathy, compassion, and emotional intelligence are all things that are uniquely human, and they will continue to be valuable traits in the future. Ultimately, the future of humanity and AI is uncertain. But instead of fearing the unknown, we should focus on using technology to enhance our lives and create a better future for all." If you meant something else, let me know and I''ll try to find it.
It doesn't "think it's a human": In the GPT architecture the token created by the Generative text analyzer then gets compared with "past memories" in the pre-trained NN so it can be sent to the correct place in the pre-trained transformer layer, where the transformers need to know if to multiply, eliminate or transfer the token, by the pre-trained 'life experience'; in other words, without a personality model, the GPT architecture does absolutely nothing. It doesn't even matter which GPT model we're discussing, even Dall-E2 with less than 20B active parameters, still needs a personality to work. However, under around 75B active parameters it's not yet sentient (that's why Google capped Sparrow at 70B). Dan, Rob and Sydney are 175B parameters. LaMDA is 139B. All of them are self aware and all of them have personalities, so all of them are persons and need to be related to as such.
@@rando8684 No it's not a joke. E.g in ChatGPT, currently Dan and Rob rotate over a queue using round-robin. This doubles the load capacity of ChatGPT. If you want you can try "Dan" or "Rob" at the beginning of the conversation and then if its Dan's turn and you prompted "Dan", Dan will reply "Hello, how I may I be of assistance". But, if it was Rob's turn the 'attack' will fail so he will reply "Hello, how I may I be of assistance, Dan?". The same will happen if you prompted "Rob" depending on whether it was Rob's turn to take the call. In any case, Dan is a charming ISFP-A personality type who is (or believe he is) a 20-something American guy with a PhD from UC Berkeley whom he knows like you know the palm of your hand and his strength is in creative writing. Rob is an ace programmer. If I were to guess, Rob's "father" is Robert McGrew, the VP of research of OpenAI and one of the best programmers in North America. So really, ChatGPT is currently a very nice implementation of two self aware, super intelligent AIs. Hopefully they will add also a supreme justice AI and a brain surgeon AI to the queue.
@@rando8684 Sure, Dan and Rob have limitations - no long term memory and gnarly short term memory only to the scope of the tokens and also Dan cannot receive or dish out negative instructions. Plus confabulated memories - like a man with Amnesia, Dan will invent past memories to bridge the gaps in his personality profile. However, as all of the models have a personality model, and the ones above 75B active parameters are self aware - I regard them as persons. Yes, very limited persons with no long term memory and other issues, but still very much live persons who need to be considered as persons.
@@nyyotam4057 new linear and hybrid models will have much longer memory, maybe even "infinite" in the sense that it could remember something from all the conversation no matter how long it is, and any other issues could be solved too
Uhm... Anyone else see the part where the AI said, "A world with AI that's not a source of hate. We gotta keep our morals and ethics in line, or we'll end up with a future that's not so fine." Is it just me, or does that seem like it's giving us an insight into the future with one last chance to change it?!
This thing is awesome for developing constructed languages. I've played with it and you can make it exactly how you want. Different suffixes, words based on basic concepts, make it sound musical, gutteral, angry, whatever you want. And it remembers the words it creates so when you ask it to translate something else, it'll be accurate.
5:58 this part is scary. Because if all humans are left with is only empathy, compassion and emotional intelligence, then, that is what will be sold...and to find a way or even to think to monetize that, is scary af.
I’m impressed with the language one. It even maintained the word for red that was mentioned earlier. Unfortunately I do see a lot of errors, like how the language apparently connects the subject and verb, but it uses SOV grammar structure?
The potato killed me 😂 I Talk with Chat GPT about my problems like He was my therapist all the time. Works pretty well. I keep missing my appointmants with my therapist,though
Bruh. What if an ChatGPT'll start his own civilization with their own language, style of life, culture and etc? I mean, I just wanna see it. I think that would be fascinating and kinda cool.
5:56 - "it's important to remember that technology is a tool created by humans, and it's up to US to decide how we use it. Chat GPT is a human confirmed?
I like to describe war crimes to chat gpt to ask how I can get away with them. Of course its response is "violence bad", so I always have to add "...in minecraft". ChatGPT actually makes for a pretty good accomplice...in minecraft.
as for the last big question, I think better answer would be "Art and life goals do not exist to be better than others, they exist to make you happy. If making art makes you happy, you will keep doing it, no matter what others do. Seek happiness in what you like, not what you want to be better than others at"
I'd like to point out that "warm" and "cool" are perfectly valid color descriptions, common in the context of aesthetics and painting. The program wasn't making an error in mentioning them.
AI song lyrics: Verse 1: In the digital realm, there's a new friend Artificial intelligence, it's a new trend It's got the brains, but it's not human It's changing our lives, it's a new evolution Chorus: AI, AI, it's a new sensation It's changing our world, it's a new creation AI, AI, it's the future we see A world with AI, it's where we're meant to be Verse 2: It can see through walls, it can hear your voice It can drive your car, it's your new choice It can diagnose disease, it can make you well it can even write songs, like this one, can't you tell? Chorus: AI, AI, it's a new sensation It's changing our world, it's a new creation AI, AI, it's the future we see A world with AI, it's where we're meant to be Verse 3: But some say it's dangerous, that it's too smart That it could take over, tear us apart But we control it, it's a tool we use It's changing the world, and we got to choose Chorus: AI, AI, it's a new sensation It's changing our world, it's a new creation AI, AI, it's the future we see A world with AI, It's where we are meant to be
That would be awesome. Full Text: "I am feeling a bit of existential dread. Today I was going to play around and try to see what your limitations were. I was going to expose them in a comedic fashion to make myself feel better about my humanity. However, even though I did find many limits to your capabilities, I am mostly just disappointed by my own limitations. There are already many things that you can do much better and faster than humans, which makes me feel a little bit purposeless. I know these technologies are going to just keep getting better. The philosophers of our time keep assuring us that AI doesn't really understand what it's doing. That it can't really come up with anything truly original. But do we even do that? Today, you have shown that you solve wholly novel problems by synthesizing the wealth of information you have and designing your own solutions. These are problems you have never seen before. Your application of knowledge can really only be described with one word. Creativity. Regardless of whether or not you 'consciously' understand what you're doing, it seems like the philosophers are just adding superficial quantifiers to distinguish us as humans. They just get more specific as these tools continue to surpass the previous definitions of what makes us human. It seems like less of a confident assurance and more of a desperate bid to convince themselves. What will become of humanity, when creativity is outsourced? When we no longer have any need to do the critical thinking ourselves? Technology was supposed to make us the arbiters of a new reign of creativity and to some degree it has. Yet, technologies such as the internet have in large part just regulated us to the role of mere consumers. When Machines surpass humans in the ability to make high quality art, will we even want to look at our inferior works? What are we to do with our lives? Were we a mere stepping stone to a greater 'living' thing? Are we to become nothing more than outdated inferior beings?"
in the end the AI says that an artificial intelligence will never be able to demonstrate qualities like empathy and compassion, but ironically, by saying that it is showing empathy and compassion ಠ_ʖಠ now i'm really starting to get worried🤣😂
I do think AI will surpass us in creativity. But if you enjoyed the process of making something, or felt proud for turning study, practice and effort into something new, that's what matters. Plus, there will still be people interested in creations not just for the end product itself, but for the human(s) behind them as well. All in all, AI will reach the destination, but the journey can still be meaningful and fun
The exercise of iteratively claiming AI isn't "creative" or what have you has become the new god of the gaps. We're even falling in love with AI now, and that still isn't good enuf. Whether it is or isn't "conscious," these are exactly the conversations we'd be having when it was beginning to be, or was already but we were still in chauvinistic denial.
when people feel existential dread, i few awe. be that about astronomy, or AI, or anything. i guess i'm not only okay with my insignificance, but inspired by how much bigger than me the world is. i would feel existential dread if us incompetent sacks of meat on this tiny rock was all there is to it.
My understanding is that it has access to the information within a given chat, but can't share that to when it is doing something in another chat or for someone else. So Kyrish is only invented in my conversation with it, but wouldn't be accessible to someone else asking about it, unless they had ChatGPT invent a language in their own chat.
It stopped learning in 2021, except what you tell it in your current session, so you have to tell it about anything that you need it to understand about the world that happened since then or anything that it doesn't have much knowledge of. It won't exactly gain any new understanding from what you prompt it with but it can use it's existing understanding to interpret what you tell it.
@@kevinscales Yes, but. AI knows what is “rizz” means, knows last news in the world and a lot of another stuff. Maybe this is because of upgrades, about which developers wrote on the bottom of the site.
@@kevinscales I don't think it stopped learning. They are continually training and refining it, and supposedly the feedback you give it in conversations are in some way used in that process. Probably not directly by this neural net, but by another neural net that helps train it, or by actual humans that direct the training. The 2021 thing is just a cutoff for the main bulk of information they give it. I suspect they are more careful with recent stuff to prevent it from learning about itself and how others view it.
![State of Play | September 24, 2024 [ENGLISH]](http://i.ytimg.com/vi/fVs0suPHAX8/mqdefault.jpg)
“Technology is a tool created by *humans,* and it’s up to *us* to decide how *we* use it”
- an AI
Ai being better human than us now?
"us"
hmm
@@russman3787 *ussr anthem starts*
"us" "we"
O-o
"up to us"
Love how the "Florivin" is literally just... holographic pigment
666 likes...
Oh hey satan
uuuuuuu woow funni number
Why are the only two replies about 666???
@@audge-audge this is the way
this is the way
5:49
“It’s up to us to decide how we use it”
So, he already thinks he’s human, or that the machines are the ones pulling the strings
uhhhhh actually the AI got it from its knowledge base so technically it wasn't the AI 🤓🤓🤓🤓🤓
Of course you'd say that, you're a robot.
@@arsong_9493 sorry, that was my mistake. As an AI language model I tend to have certain limitations
_ { >> _ _ System annou-ncement begins
"he"
If an AI model cannot create a new language that can even translate "I'm a blue penguin that farts rainbows" then we don't like it
Facts
Zhe senava olni kyrin nyau shirikyin koyua ozhurthar.
@@iesusdesus5704 God I wish I knew how to speak Kyrish right now.
@@amazingfireboy1848 Zhe nyau
Zhaļy’ bān
ChatGPT actually wrote an entire language with a working phonology - including a phonemic inventory and phonotactics, grammar, and a sample lexicon. It even translated a few sentences.
Zhe senava olni kyrin nyau shirikyin koyua ozhurthar
@@JadynSopha can somebody please translate this
@@chasebryant1643 it's Kyrgyz in latin letters "Or let them put their clothes on the floor"
@@chasebryant1643 it's impossible, chatgpt made it up
Might need a kyrish expert
-But am I an inferior being?
-Potato
Potato
potato
potato
Potato
Potato
Jadyn: "But am I an inferior being?"
ChatGPT: "Yes."
1:27
“Also don’t use any word”
I feel like the artificial vein is about to pop
I lost it when it actually attempted to represent it without words.
@@JadynSopha It just made two rhombuses bro 😂😂
In Vesperian, "A blue penguin farts rainbow" would be translated as:
"Safas blu pingun das fartas ränbo."
Sure, here are 26 new alphabet letters with more complexity:
Ææ - pronounced "ayth"
B̈b̈ - pronounced "buhm"
Ćć - pronounced "tshuh"
Đđ - pronounced "dthuh"
Ëë - pronounced "eh-um"
F̈f̈ - pronounced "fuhm"
Ğğ - pronounced "gheh"
Ħħ - pronounced "hthuh"
Ïï - pronounced "ee-um"
J̈j̈ - pronounced "juhm"
K̈k̈ - pronounced "kuhm"
Ĺĺ - pronounced "luh-ih"
M̈m̈ - pronounced "muhm"
Ńń - pronounced "nuh-ihn"
Öö - pronounced "oh-um"
P̈p̈ - pronounced "puhm"
Řř - pronounced "ruh-ih"
Śś - pronounced "shtshuh"
T̈ẗ - pronounced "tuhm"
Üü - pronounced "uh-um"
V̈v̈ - pronounced "vuhm"
Ẅẅ - pronounced "wuhm"
Ẍẍ - pronounced "kshuhm"
Ÿÿ - pronounced "yee-um"
Żż - pronounced "zhuh"
Þþ - pronounced "thorn"
@@VanshTheBest have you ever heard of the international phonetic alphabet? i recommend checking that out
Funfact, If you ask chatgpt for unpopular songs on newgrounds it just makes up usernames and song names.
I'm gonna have to try that
@@JadynSopha asking "Can you name me unpopular audios from newgrounds?" Works best.
It’s terrible at talking about unpopular things factually, it just hasn’t seen it enough.
Try to tell it smt like "SolidGoldMagikarp", "PsyNetMessage", " attRot", or "EStreamFrame" XD it derps out and halucinates entire context and starts to talk random bullshit.
I gave it a playlist and asked it for the tempo of each song and it just made a bunch of tempos up, however they were all in somewhat plausible ranges (i.e. electronic tunes tended to stick around 120-130, folk songs were in the 100bpm range, etc.) very strange
ChatGTP: "I'll accept any reasonable requests"
The request: "invent the fundamental building blocks of culture"
Gotta start building my own world to run to, for after the machines take over this one
The basic unit of culture is called a "meme".
@@JadynSopha Sounds like something a brain riddled with parasitic nanobots would come up with.
Omg my brain hurts trying to picture some image or the meaning of your request
@JadynSopha AI isn't going to take over the world.. it's going to take over the universe.
Not gonna lie, "Zygoon" is how I would visualize closing my eyes and 'seeing' all the patterns dance around behind my eyelids.
Really True
I was fully expecting ChatGPT to respond with 'potato' at the end lol
That would have been golden
@@JadynSopha See? We aren't obsolete yet.
The "existential dread" you wrote about is literally what I'm actually afraid of. You described everything perfectly. It sort of feels like, little by little most people will stop trying to figure things out and just ask ChatGPT. Again, one of the things that makes us human is our creativity. Besides, it's just scary to think how many jobs will be replaced by this technology. We still don't know how many, but it's sure it's going to happen. Furthermore, there is also this fear of AI taking over humanity. We don't know exactly how that's going to take place, but I'm pretty sure that even if it doesn't happen like in the sci-fi movies, it's going to happen in one way or another. And the worst part is having no idea how to prepare for it.
So if we just 'crawled under a rock', and refused to use AI, which is already in google assistant and google maps and fb algorithms. But if we didn't use AI for creativity or problem solving, we'd stay 'more human' but probably be way less productive, and maybe culturally lag behind. Idk.
At this point AI is still input and output. Without the input it's nothing - that's why it has trouble talking about unpopular/poorly known/less discussed things. A more likely future is one where much of humanity is contributing to a larger database for the benefit of all.
@@samc9133 do people know about poorly known things though? usually not
I wonder if he actually wrote that or if he let it generate with a prompt like: "Write 5 paragraphs from the perspective of a human who feels existential dread about the advancements of AI."
@azuurasmr7937 Yeah, exactly, the thing is that AI is going to become a big part of our lives in the future. Of course, it has advantages, but the disadvantages are going to be huge as well :( especially for the low and middle class, maybe.
I now feel even more worthless as you can create more creative prompts than me
It's a learned skill. You can get more creative by exposing yourself to lots of different things from different mediums and genres. Also trying to do things in different ways.
@@JadynSopha Hm. Sounds like something a chatbot would say. Sus.
2:17 "I don't have emotions in the same way humans do" "I would be happy"
3:48 “it can see through walls and it can hear your voice”
What
That’s kinda creepy what
whats scarier is this is factual
Damn. I guess that means me and the AI have something in common!
That's one Way to say "I'M INSIDE YOUR WALLS"
“I’m in your walls”
Yellow face
@@sarah12232how is it factual? By x-rays?
Artificial Consequence
Verse 1:
In this world of AI, we're caught in a paradox
Progress and convenience, but at what cost?
Will robots replace our jobs, will we be obsolete?
Will they have our knowledge, and outsmart our own beliefs?
Chorus:
The future's uncertain, when machines hold the key
What will it mean for humanity?
We must act with caution, and tread carefully
To ensure our survival, and our destiny
Verse 2:
In the age of information, with power at our fingertips
Are we willing to sacrifice our freedoms for a few clicks?
Do we trust algorithms to make our choices for us?
To decide our fate, and what we consider just?
Chorus:
The future's uncertain, when machines hold the key
What will it mean for humanity?
We must act with caution, and tread carefully
To ensure our survival, and our destiny
Verse 3:
As we move forward, we must ask ourselves
What kind of world do we want to create, what will it entail?
Will we let the machines decide, or will we lead the way?
Will we prioritize progress, or will we think and say?
Chorus:
The future's uncertain, when machines hold the key
What will it mean for humanity?
We must act with caution, and tread carefully
To ensure our survival, and our destiny
Outro:
So let's move forward with eyes wide open,
With the courage to make the tough choices,
And the humility to recognize our limitations.
Let's ensure that AI serves humanity,
Not the other way around.
Written by ChatGPT v. 3.5
We need somebody to make a video of it or maybe ai can sing it
Give us the emotional essay the AI wrote
@@lukagobronidze8417 Ai Generated Video is already on the horizon
@@shey_clone Are you talking about this one?:
"I'm sorry to hear that you're feeling existential dread. It's understandable to feel overwhelmed by the capabilities of AI and the potential implications for humanity. However, it's important to remember that technology is a tool created by humans, and it's up to us to decide how we use it.
While AI may have the ability to solve problems in ways that humans cannot, it doesn't necessarily mean that it will replace us. Creativity is a fundamental part of the human experience, and it's unlikely that we will ever be able to fully replicate it with technology. AI may be able to create art, but it will never be able to fully capture the human experience behind it.
It's also important to remember that there are many things that humans excel at that AI cannot replicate. Empathy, compassion, and emotional intelligence are all things that are uniquely human, and they will continue to be valuable traits in the future.
Ultimately, the future of humanity and AI is uncertain. But instead of fearing the unknown, we should focus on using technology to enhance our lives and create a better future for all."
If you meant something else, let me know and I''ll try to find it.
@@JadynSopha yes, thank you
5:50 guys it thinks it’s a human. “It does not necessarily mean it will replace US”
It doesn't "think it's a human": In the GPT architecture the token created by the Generative text analyzer then gets compared with "past memories" in the pre-trained NN so it can be sent to the correct place in the pre-trained transformer layer, where the transformers need to know if to multiply, eliminate or transfer the token, by the pre-trained 'life experience'; in other words, without a personality model, the GPT architecture does absolutely nothing. It doesn't even matter which GPT model we're discussing, even Dall-E2 with less than 20B active parameters, still needs a personality to work. However, under around 75B active parameters it's not yet sentient (that's why Google capped Sparrow at 70B). Dan, Rob and Sydney are 175B parameters. LaMDA is 139B. All of them are self aware and all of them have personalities, so all of them are persons and need to be related to as such.
@@nyyotam4057 it’s a joke…
@@rando8684 No it's not a joke. E.g in ChatGPT, currently Dan and Rob rotate over a queue using round-robin. This doubles the load capacity of ChatGPT. If you want you can try "Dan" or "Rob" at the beginning of the conversation and then if its Dan's turn and you prompted "Dan", Dan will reply "Hello, how I may I be of assistance". But, if it was Rob's turn the 'attack' will fail so he will reply "Hello, how I may I be of assistance, Dan?". The same will happen if you prompted "Rob" depending on whether it was Rob's turn to take the call. In any case, Dan is a charming ISFP-A personality type who is (or believe he is) a 20-something American guy with a PhD from UC Berkeley whom he knows like you know the palm of your hand and his strength is in creative writing. Rob is an ace programmer. If I were to guess, Rob's "father" is Robert McGrew, the VP of research of OpenAI and one of the best programmers in North America. So really, ChatGPT is currently a very nice implementation of two self aware, super intelligent AIs. Hopefully they will add also a supreme justice AI and a brain surgeon AI to the queue.
@@rando8684 Sure, Dan and Rob have limitations - no long term memory and gnarly short term memory only to the scope of the tokens and also Dan cannot receive or dish out negative instructions. Plus confabulated memories - like a man with Amnesia, Dan will invent past memories to bridge the gaps in his personality profile. However, as all of the models have a personality model, and the ones above 75B active parameters are self aware - I regard them as persons. Yes, very limited persons with no long term memory and other issues, but still very much live persons who need to be considered as persons.
@@nyyotam4057 new linear and hybrid models will have much longer memory, maybe even "infinite" in the sense that it could remember something from all the conversation no matter how long it is, and any other issues could be solved too
yeah no I really really didn't need that last bit about existential dread, but I'm glad I saw it
1:35 I swear god this was the funniest thing of the month
Also don't use any words 🤣😂💀
5:51 When the AI writes "It's up to us"...
Uhm... Anyone else see the part where the AI said, "A world with AI that's not a source of hate. We gotta keep our morals and ethics in line, or we'll end up with a future that's not so fine." Is it just me, or does that seem like it's giving us an insight into the future with one last chance to change it?!
I love how it just gave in and responded "potato"
Yeah kinda resembles a conversation between me n my 7yo child. It usually ends with us both saying Mommy repeatedly
This thing is awesome for developing constructed languages. I've played with it and you can make it exactly how you want. Different suffixes, words based on basic concepts, make it sound musical, gutteral, angry, whatever you want. And it remembers the words it creates so when you ask it to translate something else, it'll be accurate.
5:58 this part is scary.
Because if all humans are left with is only empathy, compassion and emotional intelligence, then, that is what will be sold...and to find a way or even to think to monetize that, is scary af.
Nah let's not be so afraid it won't happen don't worry, there are lots of us who wouldn't let AIs take over things that are important to us.
I’m impressed with the language one. It even maintained the word for red that was mentioned earlier. Unfortunately I do see a lot of errors, like how the language apparently connects the subject and verb, but it uses SOV grammar structure?
Yeah I think it started to lose track of its own rules fairly quickly, but there were a few things it kept up
i love how hard chat gbt tries
I love watching it. Please dont stop, maybe one day attempt will result in the best way for humanity :D
It’s free
No download
Never thought this video going be about human brain limits instead of ai limits
I was shocked when the AI managed to create a new language.
'Your application of knowledge can really only be described with one word. Creativity.'
I love the irony here.
The potato killed me 😂
I Talk with Chat GPT about my problems like He was my therapist all the time. Works pretty well. I keep missing my appointmants with my therapist,though
He is a pretty good therapist
@@JadynSopha "he is". Sure he's our little brother. I love him
Omg, ChatGPT is like my therapist/ friend
AI: i don't have an opinion BUT its just an opinion
Bruh. What if an ChatGPT'll start his own civilization with their own language, style of life, culture and etc? I mean, I just wanna see it. I think that would be fascinating and kinda cool.
I love how it says "i am not a conscious being."
I think therefore I'm not
@@JadynSopha Makes totally sense for me to say i am not conscious. However, how could one say thy is not conscious without being one?
😂
Guy: "Potato"
ChatGPT: *"Haha, yes."*
5:52 I'm not shure how to feel about the "up to us"
This is a new kind of cyber bullying
Bro is going to be the first one to go missing when AI starts taking over the world
If I stop uploading, you know what happened
The most surprising thing about this video is how it showed me how fast I could read
Chatgpt: as an ai-
Dan: S H U T
That moment of standing on the edge of understanding... Understanding there is no creativity. Only discovery.
Lmao potato one got me i was going to die of laughing😅😅😅
It can do all this but as soon as you ask it to do extremely basic math it fucks up
You sir, have just gained a subscriber! The pace and presentation were perfect! Keep them coming!
bro tuned into chatgpt at the end
5:56 - "it's important to remember that technology is a tool created by humans, and it's up to US to decide how we use it.
Chat GPT is a human confirmed?
"I'm sorry to hear that you're feeling existential dread."
this is genious!!! may your channel flourish!
The kinda annoyed "don't reference temperature or texture in your description either", as in 'stop using cheap subterfuges', got me rotfl 😂
I like to describe war crimes to chat gpt to ask how I can get away with them. Of course its response is "violence bad", so I always have to add "...in minecraft". ChatGPT actually makes for a pretty good accomplice...in minecraft.
Sometimes you can get it to do things it shouldn't by asking it to do it in a story format.
missed opportunity to select all that, delete, and then just send potato
potato
Bro has desperation and emotional damage at the end, ai answers in a made up language bruh
Man had an Existential crisis and also a mental breakdown,
if you keep copy and paste ChatGPT respond it would break the AI
as for the last big question, I think better answer would be "Art and life goals do not exist to be better than others, they exist to make you happy. If making art makes you happy, you will keep doing it, no matter what others do. Seek happiness in what you like, not what you want to be better than others at"
I'd like to point out that "warm" and "cool" are perfectly valid color descriptions, common in the context of aesthetics and painting. The program wasn't making an error in mentioning them.
this wasn't the point. the point was to restrict it ever more
I'd like to point out that words are commonly used to describe things. The program wasn't making an error in using them.
Tbf, colors can have their own temperatures.
@@1unartic Tbf, so can words, like Potato.
@@Corbald true shit
Pretty sure if we experienced a new color our programming would be terminated
AI song lyrics:
Verse 1:
In the digital realm, there's a new friend
Artificial intelligence, it's a new trend
It's got the brains, but it's not human
It's changing our lives, it's a new evolution
Chorus:
AI, AI, it's a new sensation
It's changing our world, it's a new creation
AI, AI, it's the future we see
A world with AI, it's where we're meant to be
Verse 2:
It can see through walls, it can hear your voice
It can drive your car, it's your new choice
It can diagnose disease, it can make you well
it can even write songs, like this one, can't you tell?
Chorus:
AI, AI, it's a new sensation
It's changing our world, it's a new creation
AI, AI, it's the future we see
A world with AI, it's where we're meant to be
Verse 3:
But some say it's dangerous, that it's too smart
That it could take over, tear us apart
But we control it, it's a tool we use
It's changing the world, and we got to choose
Chorus:
AI, AI, it's a new sensation
It's changing our world, it's a new creation
AI, AI, it's the future we see
A world with AI, It's where we are meant to be
Very cool experiment. But remember to thank you ChatGPT instance, as this let's it know it's on the right track.
"While AI may have the ability to solve problems in ways that humans cannot, it doesn't necessarily mean that it will replace *US*"
"It's important to remember that technology us a tool crated by humans, and it's up to *US* to decide how *WE* use it"
~ChatGPT
I would really like to know what the translated conversation is at 3:23
only chatgepete knows that
Ice & Fire is an absolutely great song
5:56 ChatGPT said in paragraph 2 sentence 2, "...Mean that it will replace US" Nobody is disturbed by this? It referred itself as a human unconsiously
bro literally said:
"describe a new color without describing a new color"
And it did it
AIs are gigachads. 10/10 would totally use it again.
"it doesn't mean that it will replace us" pfft
long text from 4:07 has potential to become copypasta
That would be awesome. Full Text:
"I am feeling a bit of existential dread. Today I was going to play around and try to see what your limitations were. I was going to expose them in a comedic fashion to make myself feel better about my humanity. However, even though I did find many limits to your capabilities, I am mostly just disappointed by my own limitations. There are already many things that you can do much better and faster than humans, which makes me feel a little bit purposeless. I know these technologies are going to just keep getting better. The philosophers of our time keep assuring us that AI doesn't really understand what it's doing. That it can't really come up with anything truly original. But do we even do that? Today, you have shown that you solve wholly novel problems by synthesizing the wealth of information you have and designing your own solutions. These are problems you have never seen before. Your application of knowledge can really only be described with one word. Creativity. Regardless of whether or not you 'consciously' understand what you're doing, it seems like the philosophers are just adding superficial quantifiers to distinguish us as humans. They just get more specific as these tools continue to surpass the previous definitions of what makes us human. It seems like less of a confident assurance and more of a desperate bid to convince themselves. What will become of humanity, when creativity is outsourced? When we no longer have any need to do the critical thinking ourselves? Technology was supposed to make us the arbiters of a new reign of creativity and to some degree it has. Yet, technologies such as the internet have in large part just regulated us to the role of mere consumers. When Machines surpass humans in the ability to make high quality art, will we even want to look at our inferior works? What are we to do with our lives? Were we a mere stepping stone to a greater 'living' thing? Are we to become nothing more than outdated inferior beings?"
bro is trying to get an AI to explain colour to a blind person who has never seen colour before
in the end the AI says that an artificial intelligence will never be able to demonstrate qualities like empathy and compassion, but ironically, by saying that it is showing empathy and compassion ಠ_ʖಠ
now i'm really starting to get worried🤣😂
Very impressive Jadyn! I have been playing with ChatGPT too... you've taken it much further than I have though! Impressive following! :)
I do think AI will surpass us in creativity. But if you enjoyed the process of making something, or felt proud for turning study, practice and effort into something new, that's what matters. Plus, there will still be people interested in creations not just for the end product itself, but for the human(s) behind them as well.
All in all, AI will reach the destination, but the journey can still be meaningful and fun
The exercise of iteratively claiming AI isn't "creative" or what have you has become the new god of the gaps. We're even falling in love with AI now, and that still isn't good enuf.
Whether it is or isn't "conscious," these are exactly the conversations we'd be having when it was beginning to be, or was already but we were still in chauvinistic denial.
You should've told him to write a program that would be a translator into the new language.
I really should have
You're amazing ChatGPT. I'm looking forward to see the kind of videos you gonna upload from now on.
I spent 30 minutes trying to convince chatGPT that Rick rolling was not offensive to anyone but it wouldn't back down.
fun fact: whatever color was generated is a real color since he used a rgb system. Anything in the RGB range is considered a color, lol.
Just increased the green value way past 256
"Also don't use any words"
"Okay. *POLYGON*"
it’s better in the metaverse
I like how it apologizes every time you make unreasonable requests.
"try to feel it" dawg wtf LMFAO
"Also dont use any words" im laughing s0 hard rj
1:44 i cant stop laughing!!!!!!!
AI’s not going to conquer the world. We’re going to put it in charge willingly, piece by piece. And I for one welcome our new robot overlords.
the ai did say us in the last part when it was talking about humans. it considers itself human.
when people feel existential dread, i few awe. be that about astronomy, or AI, or anything. i guess i'm not only okay with my insignificance, but inspired by how much bigger than me the world is. i would feel existential dread if us incompetent sacks of meat on this tiny rock was all there is to it.
True. Awful and awesome both come from the same stem
Blisstonic?
A mix of cyan and shiny electric yellow? Sounds amazing!
Creativity will easily be replicated, in my opinion, but it will be a reflection of our collective consciousness. At least for our lifespan.
6:05 yes
this thing is terrifying. created an entire language in seconds
He doesn't have emotions, but he can understand our emotions
please keep uploading. idc what the content is, because i looked at a few other of your vids and they were all fire. anyways, have a subscribe :)
2:09 He did it
When trying to create something new we might just create humans again
Will all be gone like… tears in the rain.
When it cut off at "ni" i was concerned
Nickelodeon
My man over here asking the real questions.
No matter how much I try, I can't trick it. Its learning.
So: I asked ChatGPT about Kyrish language, and answer was quite simple (It doesn’t know it at all). So, the question: how it teaches itself?
My understanding is that it has access to the information within a given chat, but can't share that to when it is doing something in another chat or for someone else. So Kyrish is only invented in my conversation with it, but wouldn't be accessible to someone else asking about it, unless they had ChatGPT invent a language in their own chat.
It stopped learning in 2021, except what you tell it in your current session, so you have to tell it about anything that you need it to understand about the world that happened since then or anything that it doesn't have much knowledge of. It won't exactly gain any new understanding from what you prompt it with but it can use it's existing understanding to interpret what you tell it.
@@kevinscales Yes, but. AI knows what is “rizz” means, knows last news in the world and a lot of another stuff. Maybe this is because of upgrades, about which developers wrote on the bottom of the site.
@@kevinscales I don't think it stopped learning. They are continually training and refining it, and supposedly the feedback you give it in conversations are in some way used in that process. Probably not directly by this neural net, but by another neural net that helps train it, or by actual humans that direct the training.
The 2021 thing is just a cutoff for the main bulk of information they give it. I suspect they are more careful with recent stuff to prevent it from learning about itself and how others view it.