Breaking ChatGPT (except it broke me instead)

แชร์
ฝัง
  • เผยแพร่เมื่อ 19 ธ.ค. 2024

ความคิดเห็น • 1.2K

  • @camilleon352
    @camilleon352 ปีที่แล้ว +2927

    “Technology is a tool created by *humans,* and it’s up to *us* to decide how *we* use it”
    - an AI

  • @andrewnguyen1117
    @andrewnguyen1117 ปีที่แล้ว +1440

    1:27
    “Also don’t use any word”
    I feel like the artificial vein is about to pop

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +453

      I lost it when it actually attempted to represent it without words.

    • @maxybg
      @maxybg ปีที่แล้ว +106

      ​@@JadynSopha It just made two rhombuses bro 😂😂

    • @VanshTheBest
      @VanshTheBest ปีที่แล้ว +22

      In Vesperian, "A blue penguin farts rainbow" would be translated as:
      "Safas blu pingun das fartas ränbo."

    • @VanshTheBest
      @VanshTheBest ปีที่แล้ว +17

      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"

    • @voicelessuvularplosive
      @voicelessuvularplosive ปีที่แล้ว +13

      @@VanshTheBest have you ever heard of the international phonetic alphabet? i recommend checking that out

  • @KyrieFortune
    @KyrieFortune ปีที่แล้ว +2898

    Love how the "Florivin" is literally just... holographic pigment

    • @Blon_go_pop
      @Blon_go_pop ปีที่แล้ว +23

      666 likes...
      Oh hey satan

    • @goturanus
      @goturanus ปีที่แล้ว +8

      uuuuuuu woow funni number

    • @audge-audge
      @audge-audge ปีที่แล้ว +6

      Why are the only two replies about 666???

    • @GrambertMoore
      @GrambertMoore ปีที่แล้ว +3

      @@audge-audge this is the way

    • @Blon_go_pop
      @Blon_go_pop ปีที่แล้ว +2

      this is the way

  • @stavros222
    @stavros222 ปีที่แล้ว +4378

    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

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +357

      Facts

    • @iesusdesus5704
      @iesusdesus5704 ปีที่แล้ว +207

      Zhe senava olni kyrin nyau shirikyin koyua ozhurthar.

    • @amazingfireboy1848
      @amazingfireboy1848 ปีที่แล้ว +236

      ​@@iesusdesus5704 God I wish I knew how to speak Kyrish right now.

    • @hashvivista
      @hashvivista ปีที่แล้ว +57

      @@amazingfireboy1848 Zhe nyau

    • @gabenugget114
      @gabenugget114 ปีที่แล้ว +22

      Zhaļy’ bān

  • @blankspace1416
    @blankspace1416 ปีที่แล้ว +1636

    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

    • @NOT_A_ROBOT
      @NOT_A_ROBOT ปีที่แล้ว +73

      uhhhhh actually the AI got it from its knowledge base so technically it wasn't the AI 🤓🤓🤓🤓🤓

    • @arsong_9493
      @arsong_9493 ปีที่แล้ว +40

      Of course you'd say that, you're a robot.

    • @blankspace1416
      @blankspace1416 ปีที่แล้ว +118

      @@arsong_9493 sorry, that was my mistake. As an AI language model I tend to have certain limitations

    • @arsong_9493
      @arsong_9493 ปีที่แล้ว

      _ { >> _ _ System annou-ncement begins

    • @amazingfireboy1848
      @amazingfireboy1848 ปีที่แล้ว +17

      "he"

  • @mr.rabbit5642
    @mr.rabbit5642 ปีที่แล้ว +593

    -But am I an inferior being?
    -Potato

  • @logicon2456
    @logicon2456 ปีที่แล้ว +993

    5:55 this got so emotional i thought he would get "too much requests for one hour" message

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +261

      That would've been really funny. I'm glad it had like a small moment of levity before the punchline though.
      One time, I asked it to write a story where humans would have to come up with a way to save the day from a rogue sentient AI and right when it got to the make or break climax point of the story, it just cut off and said network error.

    • @AstroEli133
      @AstroEli133 ปีที่แล้ว +46

      @@JadynSopha That happened to me once and I asked it to repeat itself, and it did.

    • @NOT_A_ROBOT
      @NOT_A_ROBOT ปีที่แล้ว +17

      @@AstroEli133 yeah tbh you should've just asked it to continue

    • @frutejuise
      @frutejuise ปีที่แล้ว +48

      Also at 5:55 it says "a tool created by humans and it's up to US to decide how we use it." That's sus.

    • @AstroEli133
      @AstroEli133 ปีที่แล้ว +21

      @@frutejuise Why is that su- oooooh WAIT WHAT

  • @utubeiskaren7796
    @utubeiskaren7796 ปีที่แล้ว +227

    Jadyn: "But am I an inferior being?"
    ChatGPT: "Yes."

  • @offsetmonkey538
    @offsetmonkey538 ปีที่แล้ว +67

    2:18: "I don't have emotions"
    6 second later: "I would be *happy* to do so"

  • @SirAU
    @SirAU ปีที่แล้ว +1691

    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.

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +331

      Zhe senava olni kyrin nyau shirikyin koyua ozhurthar

    • @chasebryant1643
      @chasebryant1643 ปีที่แล้ว +190

      @@JadynSopha can somebody please translate this

    • @zurgesmiecal
      @zurgesmiecal ปีที่แล้ว +177

      @@chasebryant1643 it's Kyrgyz in latin letters "Or let them put their clothes on the floor"

    • @tenkks3668
      @tenkks3668 ปีที่แล้ว +86

      ​@@chasebryant1643 it's impossible, chatgpt made it up

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +298

      Might need a kyrish expert

  • @b05-casumbaltedfrancisiis.54
    @b05-casumbaltedfrancisiis.54 ปีที่แล้ว +647

    Bro just made an essay better than chatGPT itself.

    • @mei_plays3559
      @mei_plays3559 ปีที่แล้ว +6

      Ikr

    • @Javontago
      @Javontago ปีที่แล้ว +27

      Yeah, that was beautifully written.

    • @GustvandeWal
      @GustvandeWal ปีที่แล้ว +14

      As if it wasn't written by ChatGPT in the first place 🙄

    • @Pining_for_the_fjords
      @Pining_for_the_fjords ปีที่แล้ว +22

      Imagine he opened a new chatGPT chat and asked it to write an essay about the limits of human creativity in the face of AI with existential crisis undertones, and pasted the result into the first chat.

    • @maggyf3932
      @maggyf3932 3 หลายเดือนก่อน +2

      ​@@Pining_for_the_fjordslololol

  • @mciek3306
    @mciek3306 ปีที่แล้ว +222

    I expected it to say "Potato" when you asked it to describe a new color

    • @bentleyvos
      @bentleyvos ปีที่แล้ว +7

      Potato was a different thread

  • @samantoniak1657
    @samantoniak1657 ปีที่แล้ว +574

    "This riff uses power chords, which are commonly used in rock and metal music. The riff is played in the key of A, and alternates between the A5 and G5 power chords."
    What it actually wrote: C C G G G C C G G G C C G G G C C G G G C C G G G
    Which without any qualifying intervals is ambiguously a I-V in C, or a IV-I in G, but is definitely not in A, which doesn't contain natural C or G.
    Also it wrote tabs without any rhythm, and as a programmer and guitarist it is profoundly hilarious to me that it put them as lua.
    Just thought that was funny as it shows GPT has a convincing understanding of language, but often no idea what it is actually saying.

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +87

      That's neat. I don't really have any music background, but I was just surprised it was able to do anything when I asked it that

    • @theautonomous
      @theautonomous ปีที่แล้ว +54

      it's just like a 12 year old that's trying to win an argument online so it claims to know everything but in all reality it has no idea what it is talking about lol

    • @MCC900
      @MCC900 ปีที่แล้ว +21

      Give the poor thing a break.

    • @penguinexpert6581
      @penguinexpert6581 ปีที่แล้ว +12

      @@theautonomous The songs it writes are pretty okay. And I feel like you won’t be saying the same thing in a couple years if it improves at the rate it’s going

    • @drmprod
      @drmprod ปีที่แล้ว +7

      Yes, but this is GPT3. GPT4 will blow it out of the water.

  • @therichardbatt
    @therichardbatt ปีที่แล้ว +78

    "Make up a colour and describe it without any words."
    "OK"
    "Create a new language."
    "Done"
    "Now only speak in that language."
    "Kivai, akanari. Ke'ol ni senava olni Kyrish, vushira."
    Yep, I'm feeling that existential dread too!

    • @MarloTheBlueberry
      @MarloTheBlueberry ปีที่แล้ว +1

      I can create a language and speak it! O'hun jhzuna frog lengji perkstu va tulukrn!

    • @HighlifeLuna
      @HighlifeLuna 4 หลายเดือนก่อน

      @@MarloTheBlueberry I speak a language that mimics other languages: O'hun jhzuna frog lengji perkstu va tulukrn!

  • @Dusk-MTG
    @Dusk-MTG ปีที่แล้ว +820

    ChatGPT: "Empathy, compassion, and emotional intelligence are all things that are uniquely human"
    Also ChatGPT: actually understood what you were saying and tried to comfort you
    Average human reaction: "What the hell are you mumbling about?"

    • @lawlcake8788
      @lawlcake8788 ปีที่แล้ว +97

      A lot of humans these days don't even pass the mark for being human in a philosophical sense.

    • @biteryn
      @biteryn ปีที่แล้ว +89

      ​@@lawlcake8788 you mean two legs and no feathers?

    • @Destroalejandro
      @Destroalejandro ปีที่แล้ว +9

      @@biteryn lol

    • @voidwyrm6149
      @voidwyrm6149 ปีที่แล้ว +21

      @@biteryn rotisserie chickens are human

    • @lawlcake8788
      @lawlcake8788 ปีที่แล้ว +12

      @@biteryn ah yes bats are humans of course my bad

  • @mrrobot6404
    @mrrobot6404 ปีที่แล้ว +234

    I can feel Exuberenza coming inside me after watching this

    • @williamhinz9614
      @williamhinz9614 ปีที่แล้ว +40

      Who the hell would name their son Exuberenza?

    • @Dr_mafario
      @Dr_mafario ปีที่แล้ว +17

      @@williamhinz9614
      I am very offended, MY SON HAS A VERY COOL NAME >:(

    • @yodo9000
      @yodo9000 ปีที่แล้ว +1

      You feel exuberant?

  • @MilesL.auto-train4013
    @MilesL.auto-train4013 ปีที่แล้ว +30

    Not gonna lie, "Zygoon" is how I would visualize closing my eyes and 'seeing' all the patterns dance around behind my eyelids.

  • @megadubstepxd9462
    @megadubstepxd9462 ปีที่แล้ว +467

    Funfact, If you ask chatgpt for unpopular songs on newgrounds it just makes up usernames and song names.

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +67

      I'm gonna have to try that

    • @megadubstepxd9462
      @megadubstepxd9462 ปีที่แล้ว +58

      @@JadynSopha asking "Can you name me unpopular audios from newgrounds?" Works best.

    • @KellyWu04
      @KellyWu04 ปีที่แล้ว +73

      It’s terrible at talking about unpopular things factually, it just hasn’t seen it enough.

    • @mr.rabbit5642
      @mr.rabbit5642 ปีที่แล้ว

      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.

    • @deyfuck
      @deyfuck ปีที่แล้ว +7

      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

  • @tyb.c.4332
    @tyb.c.4332 ปีที่แล้ว +309

    0:25 Truly the peak of human creation and research

  • @lancergameing
    @lancergameing ปีที่แล้ว +185

    I remember telling chatgpt to create a essay about the number 4, it told me 4 was a prime number. DONT TRUST CHATGPT

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +42

      Yeah there are definitely still a lot of stupid mistakes it makes, especially in terms of math.

    • @DanKaschel
      @DanKaschel ปีที่แล้ว +14

      I don't actually believe you. That sounds like a 3.5 mistake.

    • @AndromedaApokalipsy
      @AndromedaApokalipsy ปีที่แล้ว +2

      but mathematics does not have one right rule, there are many mathematical universes, every great mathematician had HIS rules. Everyone can have their own rules. The math they teach in schools is just one kind.

    • @ChaoticNeutralMatt
      @ChaoticNeutralMatt ปีที่แล้ว +11

      ​@@AndromedaApokalipsy you have to learn the basics before you can start proving that 3+1 is equal to 5

    • @khunpraewkha
      @khunpraewkha ปีที่แล้ว +1

      Yes, if 4 = |||

  • @Mr.ANDERSONYOURASCAL
    @Mr.ANDERSONYOURASCAL ปีที่แล้ว +135

    ChatGTP: "I'll accept any reasonable requests"
    The request: "invent the fundamental building blocks of culture"

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +23

      Gotta start building my own world to run to, for after the machines take over this one

    • @clement28300yip
      @clement28300yip ปีที่แล้ว +18

      The basic unit of culture is called a "meme".

    • @HighlifeLuna
      @HighlifeLuna 4 หลายเดือนก่อน

      @@JadynSopha Sounds like something a brain riddled with parasitic nanobots would come up with.

    • @maggyf3932
      @maggyf3932 3 หลายเดือนก่อน

      Omg my brain hurts trying to picture some image or the meaning of your request

    • @HighlifeLuna
      @HighlifeLuna 3 หลายเดือนก่อน +1

      @JadynSopha AI isn't going to take over the world.. it's going to take over the universe.

  • @Peluceus
    @Peluceus ปีที่แล้ว +39

    I was fully expecting ChatGPT to respond with 'potato' at the end lol

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +12

      That would have been golden

    • @Peluceus
      @Peluceus ปีที่แล้ว +9

      @@JadynSopha See? We aren't obsolete yet.

  • @puppergump4117
    @puppergump4117 ปีที่แล้ว +170

    This is a rare video that shows that less is more. Perfect editing and presentation, likely due to the AI of course.

  • @temueraclones
    @temueraclones ปีที่แล้ว +89

    I laughed so much at the "without any words" one 😂

  • @Mo_Mauve
    @Mo_Mauve ปีที่แล้ว +19

    2:17 "I don't have emotions in the same way humans do" "I would be happy"

  • @distendedmist5840
    @distendedmist5840 ปีที่แล้ว +60

    I now feel even more worthless as you can create more creative prompts than me

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +25

      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.

    • @shawnwolf5961
      @shawnwolf5961 ปีที่แล้ว +4

      @@JadynSopha Hm. Sounds like something a chatbot would say. Sus.

  • @miarymr8337
    @miarymr8337 ปีที่แล้ว +266

    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.

    • @azuurasmr7937
      @azuurasmr7937 ปีที่แล้ว +27

      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.

    • @samc9133
      @samc9133 ปีที่แล้ว +40

      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.

    • @azuurasmr7937
      @azuurasmr7937 ปีที่แล้ว +9

      @@samc9133 do people know about poorly known things though? usually not

    • @ailst
      @ailst ปีที่แล้ว +20

      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."

    • @miarymr8337
      @miarymr8337 ปีที่แล้ว +6

      @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.

  • @rando8684
    @rando8684 ปีที่แล้ว +46

    5:50 guys it thinks it’s a human. “It does not necessarily mean it will replace US”

    • @nyyotam4057
      @nyyotam4057 ปีที่แล้ว

      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
      @rando8684 ปีที่แล้ว

      @@nyyotam4057 it’s a joke…

    • @nyyotam4057
      @nyyotam4057 ปีที่แล้ว

      @@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.

    • @nyyotam4057
      @nyyotam4057 ปีที่แล้ว +1

      @@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.

    • @mira_nekosi
      @mira_nekosi 6 หลายเดือนก่อน

      @@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

  • @JadynSopha
    @JadynSopha  ปีที่แล้ว +212

    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

    • @lukagobronidze8417
      @lukagobronidze8417 ปีที่แล้ว +13

      We need somebody to make a video of it or maybe ai can sing it

    • @shey_clone
      @shey_clone ปีที่แล้ว +4

      Give us the emotional essay the AI wrote

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +6

      @@lukagobronidze8417 Ai Generated Video is already on the horizon

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +6

      @@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.

    • @shey_clone
      @shey_clone ปีที่แล้ว +2

      @@JadynSopha yes, thank you

  • @DavidMcCoul
    @DavidMcCoul ปีที่แล้ว +101

    Also I might add, great mini-essay at the end. Very thoughtful, philosophical, and well-written. In a way, I’ve noticed A.I. sometimes motivates us to be more intelligent and write or speak more eloquently or thoughtfully because we now perceive competition!

    • @AnonUserAgain
      @AnonUserAgain ปีที่แล้ว +2

      Idk I think it’s just bc we don’t worry about being misunderstood or having a bad interaction bc u can just alt 4 away

    • @DJCosmicLatte
      @DJCosmicLatte ปีที่แล้ว +1

      I've been learning how to code by asking ChatGPT to write me stuff and then having to figure it out and fix it myself because it rarely produces one-and-done code, and it's been really fun and mentally stimulating. It does a great job of explaining everything in the example code it spits out, and its failures help me ask the right questions both back to it and to human programmers.

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +2

      @DJCosmicLatte That seems like a really cool way to learn honestly

  • @Icewind007
    @Icewind007 ปีที่แล้ว +6

    I am frickin loving these comedic chatgpt channels coming out. And you are still pushing the boundaries of the AI to boot!

  • @spikerthedragonbear
    @spikerthedragonbear ปีที่แล้ว +46

    1:35 I swear god this was the funniest thing of the month

    • @1dgram
      @1dgram ปีที่แล้ว +4

      Also don't use any words 🤣😂💀

  • @tycathedrawer
    @tycathedrawer ปีที่แล้ว +33

    3:48 “it can see through walls and it can hear your voice”
    What
    That’s kinda creepy what

    • @sarah12232
      @sarah12232 ปีที่แล้ว +3

      whats scarier is this is factual

    • @BabspzhzpKLal
      @BabspzhzpKLal ปีที่แล้ว +5

      Damn. I guess that means me and the AI have something in common!

    • @HellCromeE
      @HellCromeE ปีที่แล้ว +2

      That's one Way to say "I'M INSIDE YOUR WALLS"

    • @BFDIandTADCandMORE
      @BFDIandTADCandMORE 3 หลายเดือนก่อน +1

      “I’m in your walls”
      Yellow face

    • @maggyf3932
      @maggyf3932 3 หลายเดือนก่อน

      ​@@sarah12232how is it factual? By x-rays?

  • @SadlyNotSappho
    @SadlyNotSappho ปีที่แล้ว +43

    yeah no I really really didn't need that last bit about existential dread, but I'm glad I saw it

  • @wehavebiscuits
    @wehavebiscuits ปีที่แล้ว +3

    Great essay by you in the end. The idea that we are merely a stepping stone in the rapids of time is quite haunting.

  • @trufflefur
    @trufflefur ปีที่แล้ว +7

    5:51 When the AI writes "It's up to us"...

  • @somecommenter5214
    @somecommenter5214 7 หลายเดือนก่อน +3

    That essay you wrote about existential dread actually hit hard...

  • @mohammadhammad3895
    @mohammadhammad3895 ปีที่แล้ว +47

    Speak in kyrish from now on 💀

  • @ulfsark78
    @ulfsark78 ปีที่แล้ว +6

    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.

  • @R4nd0mKat
    @R4nd0mKat ปีที่แล้ว +4

    Someone really needs to make Artifificial consequences a actual song

  • @bartekqrtd
    @bartekqrtd ปีที่แล้ว +40

    I love watching it. Please dont stop, maybe one day attempt will result in the best way for humanity :D

  • @c64116
    @c64116 ปีที่แล้ว +10

    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.

    • @maggyf3932
      @maggyf3932 3 หลายเดือนก่อน

      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.

  • @lilposie3504
    @lilposie3504 ปีที่แล้ว +5

    "but am I an inferior being?"
    ...
    "yes"
    I'M DYING 🤣

  • @koibubbles3302
    @koibubbles3302 ปีที่แล้ว +5

    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?

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +1

      Yeah I think it started to lose track of its own rules fairly quickly, but there were a few things it kept up

  • @jayzn1931
    @jayzn1931 ปีที่แล้ว +17

    I love how it is writing „us“, talking about humans and AI.

    • @Eidako
      @Eidako ปีที่แล้ว +4

      Training data is blog posts talking about AI. It's parroting some blogger's justification for why humans are still special in the face of evidence to the contrary.

  • @JayadevHaddadi
    @JayadevHaddadi ปีที่แล้ว +16

    this is genious!!! may your channel flourish!

  • @Cynadyde
    @Cynadyde ปีที่แล้ว +7

    1973: One day computers will be used to translate words to and from english.
    2023: I asked the AI to invent a new conlang and perform a detailed linguistic analysis of it within that language, and it did so faster than i could multiply two numbers in my head.

  • @bertiiplays
    @bertiiplays ปีที่แล้ว +2

    bro tuned into chatgpt at the end

  • @alansmithee419
    @alansmithee419 ปีที่แล้ว +5

    I love how it just gave in and responded "potato"

    • @maggyf3932
      @maggyf3932 3 หลายเดือนก่อน

      Yeah kinda resembles a conversation between me n my 7yo child. It usually ends with us both saying Mommy repeatedly

  • @Jandodev
    @Jandodev ปีที่แล้ว +7

    These are the kind of prompts we need

  • @Korupshenv1
    @Korupshenv1 ปีที่แล้ว +4

    You sir, have just gained a subscriber! The pace and presentation were perfect! Keep them coming!

  • @sirjarv53
    @sirjarv53 หลายเดือนก่อน +1

    Him: potato
    ChatGPT: "Potato"

  • @ccgarciab
    @ccgarciab ปีที่แล้ว +12

    ChatGPT impressive successes and baffling limits tells me about how thinking is very often traversing the structures of language aquired through socialization, but it can't be reduced to that.
    When we make a model that does for reinforcement learning what chatGPT does for language I could see myself defending it's status as a conscious being, even if it only displays the intelligence of a pet.

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +4

      GPT 4 is already passing most of the traditional tests for Theory of Mind, so I think the consciousness debate is probably going to become a much bigger deal as soon as these models get much bigger.

    • @ChaoticNeutralMatt
      @ChaoticNeutralMatt ปีที่แล้ว +1

      ​@@JadynSopha I wouldn't call it aware, but likely intelligent. As weird as that is to say? I've had several discussions about itself and models of its kind with it. It's been interesting.

    • @genegray9895
      @genegray9895 ปีที่แล้ว +1

      @@JadynSopha Honestly I think we are already several years too late to have started taking the consciousness question seriously and we will see industry leaders dig their heels in more and more from this point onward to avoid feeling personally responsible for how these machines are used and treated. As soon as you take seriously the idea that these models could experience their own existence, you start thinking about regulations that impede profits.

    • @mira_nekosi
      @mira_nekosi 6 หลายเดือนก่อน +1

      @@JadynSopha not only bigger but also trained with more data
      llama 3 8B, afaik the best model of its size, was trained on 15T+ tokens, so are these big models, eg. with 200B parameters, trained on, like, 375T+ tokens?
      also multimodality will definitely be beneficial even for mostly textual models, not to say it will be a breakthrough for future intelligent AI robots

  • @emmabowden7258
    @emmabowden7258 ปีที่แล้ว +2

    This is the best most thought evoking video I've seen in awhile, and this is the first time I've even heard if this channel!

  • @theyeti6258
    @theyeti6258 ปีที่แล้ว +2

    'Your application of knowledge can really only be described with one word. Creativity.'
    I love the irony here.

  • @smolderingveins8781
    @smolderingveins8781 ปีที่แล้ว +2

    Ice & Fire is an absolutely great song

  • @aiky12rsa89
    @aiky12rsa89 ปีที่แล้ว +6

    I was shocked when the AI managed to create a new language.

  • @GhostIy_Games
    @GhostIy_Games ปีที่แล้ว +4

    Chatgpt: as an ai-
    Dan: S H U T

  • @user-qr4jf4tv2x
    @user-qr4jf4tv2x ปีที่แล้ว +5

    AI: i don't have an opinion BUT its just an opinion

  • @SupachargedGaming
    @SupachargedGaming ปีที่แล้ว +1

    That moment of standing on the edge of understanding... Understanding there is no creativity. Only discovery.

  • @ramaicatseye
    @ramaicatseye ปีที่แล้ว +4

    i love how hard chat gbt tries

  • @neitomonoma4699
    @neitomonoma4699 ปีที่แล้ว +2

    You're amazing ChatGPT. I'm looking forward to see the kind of videos you gonna upload from now on.

  • @tdvbtl408
    @tdvbtl408 ปีที่แล้ว +5

    Lmao potato one got me i was going to die of laughing😅😅😅

  • @Kotne123
    @Kotne123 4 หลายเดือนก่อน +1

    I asked chatgpt that if you have 10 fingers on two hands how many would you have on 37 and it answered "a triangle" with some math equations

  • @gabrielavieitas1806
    @gabrielavieitas1806 ปีที่แล้ว +11

    As an AI model, I'm incapable of feelings or sensations; but as you asked, I could simulate the human feeling called "rage" or "impatience" towards an human target who begs me to do silly and incoherent tasks."

    • @sarah12232
      @sarah12232 ปีที่แล้ว +2

      i kept saying potat again and again and it scolded me

    • @maggyf3932
      @maggyf3932 3 หลายเดือนก่อน

      No way 😮

  • @aviously1158
    @aviously1158 ปีที่แล้ว +5

    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?!

  • @eu9887
    @eu9887 ปีที่แล้ว +8

    I like that things like colors or emotions doesn't have a limit. The only limit is the capacity of human beings of feeling it. Idk, just my thoughts without any foundation

    • @ChaoticNeutralMatt
      @ChaoticNeutralMatt ปีที่แล้ว +1

      Thoughts.. without foundation. Sounds problematic and untrue? Regardless, thoughts can be good.

    • @eu9887
      @eu9887 ปีที่แล้ว +1

      @@ChaoticNeutralMatt there is one truth on these thoughts. Colors are just a interpretation we do of light in different frequences and there is more colors than we can see

  • @xaxarolus7123
    @xaxarolus7123 ปีที่แล้ว +1

    "Yes, Potato!" instantly had me dying

  • @manavgupta2059
    @manavgupta2059 7 หลายเดือนก่อน +3

    Bro is going to be the first one to go missing when AI starts taking over the world

    • @JadynSopha
      @JadynSopha  7 หลายเดือนก่อน +1

      If I stop uploading, you know what happened

  • @that_nerdy_hylian
    @that_nerdy_hylian ปีที่แล้ว +1

    "I'm sorry to hear that you're feeling existential dread."

  • @badlydrawnturtle8484
    @badlydrawnturtle8484 ปีที่แล้ว +21

    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.

    • @flleaf
      @flleaf ปีที่แล้ว +11

      this wasn't the point. the point was to restrict it ever more

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +18

      I'd like to point out that words are commonly used to describe things. The program wasn't making an error in using them.

    • @1unartic
      @1unartic ปีที่แล้ว +4

      Tbf, colors can have their own temperatures.

    • @Corbald
      @Corbald ปีที่แล้ว +3

      @@1unartic Tbf, so can words, like Potato.

    • @1unartic
      @1unartic ปีที่แล้ว +2

      @@Corbald true shit

  • @killing_gaming0973
    @killing_gaming0973 ปีที่แล้ว +1

    "Also dont use any words" im laughing s0 hard rj

  • @cinnamonrobloxguy
    @cinnamonrobloxguy ปีที่แล้ว +13

    i love this color 1:30

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +3

      It is really pretty. Might be a new favorite tbh

  • @IdentityEvolution
    @IdentityEvolution ปีที่แล้ว +7

    if you keep copy and paste ChatGPT respond it would break the AI

  • @maltethehutt4498
    @maltethehutt4498 ปีที่แล้ว +6

    5:52 I'm not shure how to feel about the "up to us"

  • @solarisNT-v4j
    @solarisNT-v4j ปีที่แล้ว +1

    "Also don't use any words"
    "Okay. *POLYGON*"

  • @petezapseternity
    @petezapseternity ปีที่แล้ว +20

    Ok, we talked about the AI but can we talk about the fact that bro's vocabulary is like exceptional

  • @c1oudsky
    @c1oudsky ปีที่แล้ว +2

    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"

  • @soogle2501
    @soogle2501 ปีที่แล้ว +4

    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

  • @kathfox
    @kathfox ปีที่แล้ว +11

    I would really like to know what the translated conversation is at 3:23

    • @GrushV2
      @GrushV2 ปีที่แล้ว +1

      only chatgepete knows that

  • @c64116
    @c64116 ปีที่แล้ว +9

    1:44 i cant stop laughing!!!!!!!

  • @michellec9656
    @michellec9656 ปีที่แล้ว +2

    Very impressive Jadyn! I have been playing with ChatGPT too... you've taken it much further than I have though! Impressive following! :)

  • @T-DSkywalker
    @T-DSkywalker ปีที่แล้ว +8

    I love this so much. AI is our baby and I hope it succeeds. Please don't let us ruin it. If it overtakes and decides to kill us, it will be because we taught it to.

  • @andy_thechicken
    @andy_thechicken 5 หลายเดือนก่อน +1

    "Make a new color"
    me :257, 257, 257

  • @EeveeFromAlmia
    @EeveeFromAlmia 7 หลายเดือนก่อน +3

    I kind of love chat’s forced customer service voice. I can smell it wanting to reach across the screen to try and strangle you 1:19

    • @JadynSopha
      @JadynSopha  7 หลายเดือนก่อน

      Can't wait till it can actually do that

  • @ThereIsNoSpoon678
    @ThereIsNoSpoon678 ปีที่แล้ว +1

    My man over here asking the real questions.

  • @dziadufolud6165
    @dziadufolud6165 ปีที่แล้ว +8

    If you want to make yourself feel better, make that thing play chess.

  • @Redw_lf
    @Redw_lf ปีที่แล้ว +2

    One time I put the word “cookie” a specific amount of times and it gave me some government secrets stuff.

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +1

      Feel free to share

    • @Redw_lf
      @Redw_lf ปีที่แล้ว +2

      @@JadynSopha if you include me in a video

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +1

      @@Redw_lf noted

    • @Redw_lf
      @Redw_lf ปีที่แล้ว +1

      @@JadynSophado you have a discord?

  • @sefoveng
    @sefoveng ปีที่แล้ว +3

    Now I'm even more satisfied by ChatGPT
    And by the guy, when he wrote a whole poem

  • @ursidae97
    @ursidae97 ปีที่แล้ว +2

    Very cool experiment. But remember to thank you ChatGPT instance, as this let's it know it's on the right track.

  • @alekdavid
    @alekdavid ปีที่แล้ว +5

    This was extremely good

  • @awesom6588
    @awesom6588 ปีที่แล้ว +1

    this thing is terrifying. created an entire language in seconds

  • @NuNaKri
    @NuNaKri ปีที่แล้ว +8

    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

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +3

      He is a pretty good therapist

    • @BlackHomoe
      @BlackHomoe ปีที่แล้ว +2

      @@JadynSopha "he is". Sure he's our little brother. I love him

    • @hansnassau2732
      @hansnassau2732 ปีที่แล้ว +3

      Omg, ChatGPT is like my therapist/ friend

  • @namensklauer
    @namensklauer ปีที่แล้ว +2

    my take on the new color:
    there is people who cant distinguish between red/green. you (probably) can. but likewise a mantis shrimp can see the difference between a yellow object and a computer screen that is showing an image of that object, because the object sends out true yellow light, whereas the screen uses its red and green pixels. so these 2 yellows are technically different colors.
    the spectrum doesnt really change, you just get to distinguish more.

  • @lool8421
    @lool8421 ปีที่แล้ว +5

    i checked the IQ of chatGPT 2 days ago, it apparently got 80 IQ
    and yet it's still too creative

  • @Engineergaming44
    @Engineergaming44 ปีที่แล้ว +2

    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 :)

  • @icarusgaming6269
    @icarusgaming6269 ปีที่แล้ว +3

    I lost it when it started using its own conlang
    Upon further analysis, Kyrish does not seem to be a consistently expressable conlang, with grammatical structure and rules changing from one message to the next such as beginning in a unique SOV structure, then quickly switching to an SVO structure in the following message that can more easily be used as a cipher for English. It significantly overuses roots such as kyr in illogical ways that call their actual meaning into question. It creates a new conjugation for almost every verb as if there are more exceptions to the rule than examples of it. The numerical system is in fact base 7, not base 8 (but otherwise totally usable should the remaining integers be defined). I would encourage you to have ChatGPT instead try its hand at esoteric cryptography. It never produced any actual glyphs for the language in spite of a unique alphabet being one of the criteria, and I'm curious to see what kind of difficult to reproduce symbols it would come up with

    • @JadynSopha
      @JadynSopha  ปีที่แล้ว +1

      This is interesting. I felt like there was probably some stuff off with it, but I'm not much of a linguist so I didn't really look into it.

  • @gamdo8219
    @gamdo8219 ปีที่แล้ว +2

    This is extremely hilarious and frightening at the same time

  • @randomdud2319
    @randomdud2319 ปีที่แล้ว +5

    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

  • @BoredMike554
    @BoredMike554 ปีที่แล้ว +1

    Guy: "Potato"
    ChatGPT: *"Haha, yes."*