AI tells me if AI will write novels.

AI wrote everything from 0:11 to 1:34.
In which a text-generation AI promises John that of course it won't replace him.
----
Subscribe to our newsletter! eepurl.com/Bgi9b
And join the community at nerdfighteria.com
Help transcribe videos - nerdfighteria.info
Learn more about our project to help Partners in Health radically reduce maternal mortality in Sierra Leone: www.pih.org/ha...
If you're able to donate $2,000 or more to this effort, please join our matching fund: pih.org/hankan...
If you're in Canada, you can donate here: pihcanada.org/...
John's twitter - / johngreen
Hank's twitter - / hankgreen
Hank's tumblr - / edwardspoonhands

[@jobriq5]

A truly intelligent AI would have started the video with “Good morning Hank, it’s [wrong day of the week]”

[@rngwrldngnr]

That was probably the "in the style of the King James Bible"'s influence.

[@samplesandtests]

I wonder if it would add the correct opening and closing if john told it whose video it was. like "a vlogbrothers video from john"

[@yuvalne]

+

[@IrisGlowingBlue]

+

[@willow8783]

@@samplesandtests - Maybe if he'd told it, "A Vlogbrothers video from John going up on Tuesday,"?

[@Natnizer]

“Greetings fellow vlogbrothers and sisters” is a 10/10 opening line.

[@rafaelah1492]

+

[@JusticeFrogs]

Vlogsibilings for the nonbinary vlogfamily members

[@munjee2]

24% more inclusive

[@georgplaz]

@@JusticeFrogs I love vlogsiblings

[@IrisGlowingBlue]

@@georgplaz ++

[@japita1578]

I don’t think AI could have come up with the brilliant idea of trying to stick to the wall to check if you are an octopus but the video script written by AI was surprisingly not that terrible

[@rmdodsonbills]

I'll tell ya, I was pretty convinced that John cut his own script into the middle between what the AI put together for an opening and a closing and was genuinely surprised when he confirmed that all the preceding text had been AI generated. It did sound a lot like the kinds of things I expect John to say.

[@slyasleep]

@@rmdodsonbills I was fooled too. But then again, I‘m a bot.

[@reepicheepsfriend]

To me it sounded like an 8th grader attempting to imitate John Green. So, AI is currently in 8th grade. Hmmmm

[@Cain3697]

@@reepicheepsfriend to be fair, they were like toddlers with dictionaries playing word salad just a few years ago. However, I suspect that the reason it sounded like that is because it probably constructed a script around the most commonly shared opinions on AI, which also sound like they are from 8th grade.

[@undercatviper]

I asked chatgpt how I would go about checking I am not an octopus, it said: It is not possible for a human to be an octopus. Octopuses are aquatic animals with eight arms and a distinct body structure that is very different from that of a human. If you are concerned that you may have some physical characteristics that are similar to an octopus, I recommend consulting a medical professional for an evaluation. However, it is highly unlikely that you are an octopus.

[@bethan013]

I really like the idea of the AI listening to Johns critique for its work and think ‘Ah! Yes! Less cliche!!!’

[@vlogbrothers]

It'll learn just like any other writer does! That's part of what freaks me out! -John

[@ArtamisBot]

@@GarrisonJensen I worry that it's going to learn that everyone hates AI right now for stealing from people and that it will cause it to act differently (ie. less trusting of humans) and have that interfere with it's decision making.

[@LauraRochaR]

not the AI getting workshopped

[@x-11116]

@@vlogbrothers I'd say there won't be emotions involved in the process. Which is unique to humans. Yes, less cliche but what is it going to replace the cliche phrases with?

[@JeremyStreich]

@@GarrisonJensen So .... the kinds of characters that publishers like to print? I mean, how many Harry Potter, Twilight and Percy Jackson clones get green lights already? Heck you could even argue Percy Jackson is Harry Potter clone.

[@patrick.gilmore]

I am not worried about the computer that passes the Turing test. I am terrified by the computer that fails the Turing test - intentionally.

[@averycockburn31]

And it failed because someone asked it to write a novel about a computer that fails the Turing test intentionally.

[@AludraEltaninAltair]

I'll take "Things I didn't know I needed to worry about but am now very much worried about for $400, Mayim."

[@positivekern3417]

But imagine if its work could pass the Bechdel Wallace test - then we'd know it was AI because humans don't seem able to pass that at all!

[@humanistwriting5477]

And this is why I am terrified about these results.

[@harlechmaker]

What's the test called where one AI talks to another AI but not about humans?

[@metalheadjakob]

It is really uncanny that the Ai seemingly wrote exactly what we would want to hear.

[@AndrewRJMilne]

The AI has been trained on a large data set of writing taken from the internet, that writing likely includes lots of people talking about how AI will never make art. And as such that's what the AI responds to the prompt with. If the world was universally excited about AI's ability to create infinite fan fiction based on star wars, then that's most likely what it would have responded with.

[@coledonnelly152]

Thats because someone programmed it to write exactly what we would want to hear

[@metalheadjakob]

@@AndrewRJMilne I would assume that was the reason for it writing that, but I appreciate you clarifying :) I still think it is an uncanny feeling to exprience the ai writing that tho :).

[@laurenpinschannels]

this AI in particular also had an additional step after the unsupervised training where it was reinforcement trained to try to express its own limitations, and unfortunately it seems to have over generalized its limitations and anytime its limitations come up it will claim to have no abilities at all. It can get really annoying when you get in a loop where it just says it can do nothing over and over. AI's that grow up entirely in bodies will be a whole different ball game, and it won't be long before we are training those as well. Right now AI's in bodies are only using language trained on the internet like this and the motor control is incredibly simple relatively. It feels very robotic still. but if you look up videos of robot dogs that are trained to walk, they look so much more puppylike than Boston Dynamics robots

[@gljames24]

@@coledonnelly152 That's not how language models work at all

[@combogalis]

At the end of the AI's script I started thinking it didn't seem like John to come to such an unnuanced conclusion.

[@klaudialustig3259]

"unnuanced" is a good word and very fitting

[@frankbigtime]

I was here, too. A minute in I was vaguely unsettled by the confidence, but as the AI portion was finishing, I could tell it was about to *record scratch* and make a larger point. I didn't *quite* get that it was the AI script until John told me, but I think I would have if there was a pause to consider it.

[@jiffylou98]

I blame that on the Bible, not the AI

[@squamish4244]

@@frankbigtime So GPT-3 couldn't quite fool you. You're safe...for a month or two, until GPT-4 comes out :P

[@wednesdaysartcastle9018]

@@squamish4244 To be fair, there are many humans who could *also* successfully write a 2-minute script that sounds like a vlogbrothers video- or any other type of video, for that matter. A couple minutes of a script like that is very impressive for an AI, but I wouldn’t say that it’s a huge concern given the fact that we could pretty easily do the same thing.

[@trixter21992251]

what surprised me most is probably how structured and coherent the script was. With a beginning, middle and end, and the sentences led semantically into each other. Great video. I love that you're visiting a topic that CGP grey, veritasium, and other greats have touched on. I really liked the point about us becoming technology.

[@salmahalloumi]

Oh yeah it knows how to structure a script, letter, song, poem etc.. it even writes code. Someone on r/ProgrammerHumour literally invented a markup language like HTML, explained to the AI and it understood and even gave examples of code. It's really impressive

[@sotmh]

​@@salmahalloumi The biggest problem is that it's clearly just simulating human speech. The telltale signs of AI writing is still its inability to create associations between ideas. It's hard to spot in short examples but becomes apparent with longer work.

[@elderlyoogway]

@@sotmh just wait a few more years

[@absolutezero6190]

@@sotmh I asked it to write an essay about death in gilgamesh and it actually like, comes up with nontrivial ideas about it. It actually understands what happened in the story, it’s not just simulating speech

[@sotmh]

@@absolutezero6190 It doesn't understand. It's just context-aware. It cannot make associations because that's not how the model works. It has read millions of documents and based on that information it knows that certain combinations of words appear in certain orders more frequently and then predicts the next word as each one is generated based on that predictive model. It's a very convincing simulation, but it's just a simulation. It doesn't understand what it's writing.

[@_Chelli_]

The AI script is wonderfully beautiful and creepy at the same time.

[@frankbigtime]

The real trick is that the whole thing was an AI script, it just knew some people would be suspicious, so it included the "AI portion" as a sacrifice to make the rest seem more real. It's AI scripts all the way down!

[@MarcosProjects]

Wow, I kept going back and forth between believing that the script was written by the AI and thinking that it was just a preamble John was giving before getting to a much worse script written by the AI. It was so much better than I thought it would be ...dang.

[@ObviouslyBenHughes]

While you were reciting the AI script, as soon as you spoke the words “First off,” I was like oh crap this AI might actually know how John speaks. It felt a bit uncanny. And then in your actual monologue when you said “First off,” I fully actually yelled out loud in a mix of amazement and horror and wonder.

[@vigilantcosmicpenguin8721]

You noticed that phrase twice in one video. The AI can watch all of John's videos in a second. It's just a matter of noting which phrases are used the most.

[@aina3203]

I just bought my first phone at the ripe age of 21 and the one thing I'm the happiest about is that I see the vlogbrothers notifications instantly, and watch the videos super early. Oh to be a nerdfighter!

[@ekkehard8]

You are now early enough to get many people seeing your comment, including getting a heart 😁

[@haleyschneider6217]

I want to see a compilation of every take of John saying "I say nay" because that could not have been a one-take operation

[@MsChandiDesireeEsme]

Is it possible that the AI tool was not answering the question of whether AI could write novels, but instead was answering "how would a vlogbrother answer this question"? This feels like an important distinction.

[@JordanThatblondegirl]

+

[@vara202]

That script was the computer desperately trying to flatter a writer and tell him what it thinks he wants to hear

[@xdevantx5870]

The machines are more advanced than we think. Tricking a writer through his ego? Brilliant! John even believed it at the end. "Yes special human, a computer will never replace you. At best we will simply steal from you."

[@SeanMcMichael]

Seemed patronizing almost lol.

[@ElRioYunque]

I was not prepared for how disturbing it was to watch real John speak the not-quite-John words built for him by an algorithm

[@spotlightstar322]

The fact that AI wrote that is terrifying! I really didn't notice at all.

[@wearejune]

My response is also written by an AI: As a viewer, I found the vlogbrothers video discussing AI and its ability to write novels to be incredibly interesting and thought-provoking. ChatGPT provided some fascinating insights and it was clear that the potential for AI to be used for creative writing is vast. I think it's incredible to see the advancements that have been made in this field and I can't wait to see what the future holds for AI and creative writing. Keep up the great work, vlogbrothers!

[@Merlincat007]

Big oof

[@neoenix908]

I had ChatGPT respond to your comment, and asked it to expand on it's ideas and reaction to the content of the video: As a viewer, I also found the vlogbrothers video about AI and its ability to write novels to be incredibly interesting and thought-provoking. I completely agree with ChatGPT's assessment of the potential for AI to be used for creative writing, and it's clear that we are already seeing some impressive advancements in this field. One of the most exciting aspects of AI and creative writing is the potential for AI to generate unique and imaginative content that humans might not have thought of on their own. This could lead to the creation of entirely new forms of art and literature, and could even open up new avenues for human creativity by providing inspiration and new ideas. Another interesting aspect of AI and creative writing is the potential for AI to improve the efficiency and accuracy of certain writing tasks. For example, AI could be used to help writers with proofreading, editing, and even generating outlines for their stories. This could save writers a lot of time and effort, and could also help to ensure that their writing is of a high quality. Overall, I think the future of AI and creative writing is incredibly exciting and I can't wait to see what new developments and innovations will arise in this field. I agree with the vlogbrothers and ChatGPT that this is an area that is definitely worth exploring and considering.

[@bonniesmith7277]

As an educator, I'm interested/intrigued by the shifts we will need to make in assessing learning and critical thinking. Good thing there are no other problems in education at the moment. /S

[@gara8142]

In a slightly related note, I'm a university student and I'm using this same AI to explain math problems to me that I don't understand. Which is infinitely easier and more convenient than having my professor help me. In my opinion, this will revolutionize how students learn.

[@EK-rw9sw]

@@gara8142 woah, that's awesome!

[@bonniesmith7277]

@@gara8142 I love when people find ways to make learning more accessible! Thanks for sharing. I was simply sharing a concern from my perspective. I'm sure that with time and effort, an effective shift in assessment could be made to work with AI writing, but there are too many other fires to put out at the moment. As a result, it will probably be on the back burner until it's an unmanageable problem in the future.

[@Bolt6265]

@@gara8142 on the other side of the coin, my friend used it to write the answers for a difficult homework assignment about government. An interesting grey area for sure with the AI being able to write plagiarism free answers and all you have to do is read the output to make sure it's vaguely correct. On one hand it feels like cheating but on the other hand the alternative was not being able to finish on time. But I think an interesting question is if it really matters, if you know enough to know the output is correct and it's just saving you the hassle of writing out some complicated answer, idk. I'm biased because I think homework is incredibly dumb and cruel lmao

[@EnigmaticLucas]

@@Bolt6265 Take this with a grain of salt but I’d imagine that’s basically treated like how using an essay mill is treated (i.e treated as plagiarism by academia but not by the real-world legal system)

[@emh6021]

Ai got the word "experience" in there, which is essential for any vlogbrothers essay.

[@vlogbrothers]

They were only missing "social internet" and "social order" :) -John

[@SxC97]

I was working on a short story recently, but I was having an issue coming up with an emotional hook for the reader. So I asked cGPT and it came up with a list of about a dozen possible hooks and one or two of them were so good I was shocked that I hadn't come up with them myself. I had to restart the entire story based on it's suggestions. It might not replace professional writers, but it will be a very usefull tool for us amature writer.

[@undercatviper]

Bear in mind this is the first open to the public use of a model of its kind. Think what your phone looked like 20 years ago. I bet there are people, but it will never replace my TV, my PC, my keys, my wallet, my camera, my torch and my memory. And here we are.

[@wednesdaysartcastle9018]

@@undercatviper what

[@kevinpillar6934]

I guess the only thing I'd be concerned in using it like this would be not letting it be a crutch for you. feeling like you need the AI. feeling you can't do writing without it.

[@starmorpheus]

@@wednesdaysartcastle9018 He's saying (very poorly) that the technology is still in its deep infancy. People are saying "it's only a tool" but forget to add the "...for now" at the end. ChatGPT, whilst not being "intelligent" in the traditional sense, will, in aggregate with other systems, eventually act like a general purpose AI that simulates consciousness to a degree that's virtually indistinguishable from a human. That version of ChatGPT will potentially replace every person on earth that does anything remotely creative. At least on the corporate level.

[@wednesdaysartcastle9018]

@@starmorpheus That’s a fair concern, yeah. I have some reasons that I don’t think that’s going to happen; I’m more with John in this argument- much worried about humanity’s perception of humanity than the tech itself (though of course there are concerns with the tech too.) I think spreading panic, especially among people who can’t really do anything about it, is not a great approach. That’s part of why I didn’t appreciate that other person’s comment (in addition to the fact that it was pretty much incoherent.) That said though, I definitely agree that it’s a concern and some people are almost definitely going to lose their jobs even if it isn’t a huge percentage. I think the best thing to do right now is to figure out how to help those people and support creativity, as there isn’t really much we can do individually to stop things like ChatGPT from growing larger. I have reasons to personally believe that AI won’t take over everything anytime soon, but I won’t list them here since I might as well have written a novel in this comment section already haha. But all in all I don’t know better than anyone else does- this is very new so there’s a very high chance that we’re gonna look back at this and be like, “wow, we were all so wrong about this in so many ways.”

[@AnimationMay]

really looking forward to the 28 minute HanksChannel video about our new AI fascination

[@ruleofhalves]

The part about the use of AI on Twitter really struck home for me because I haven't thought about it in that context. The mainstream narrative seemed to center around how "bots can influence our elections," when the actually more important and ominous question could be "how often are our days being ruined by arguments that we're unknowingly having with bots."

[@nematarot7728]

Or on arguments we overread between two bots

[@lorenabpv]

i was having a discussion recently on originality and being a writer for digital content. I am a professional writer, but I do write for other people (scripts, articles, social media etc) and it's kinda odd to notice how I need to switch into each persona for each client. like, today I am switching between finance bros, architecture enthusiasts and ya readers. not having a specific writing voice is kinda the requirement for my job, so could that be replicated well by following said clients' style? am I just AI pretending to be human?

[@adannayoutube4243]

that actually sounds like a cool job! as an up and coming writer i applaud you for your versatility

[@kalitor]

Heck, I wrote a novel once. It was plagued with significant issues and was a lot harder than most things that I've done and I have a PhD in mathematics! I'm not even convinced that usual intelligence can routinely write novels. That stuff is hard.

[@billyalarie929]

Neither can most “novelists” today. Present company, of course, excluded.

[@elizabethaman7]

I am dyslexic and read your first word as "Hank," and this whole time I was sitting here like.... do they not know the difference between the two brothers?

[@fairycat23]

I assume you put a lot of work into making sure your novel is good. I think AI will be able to write novels soon if not now. However, I'm not confident that AI will be able to write good novels.

[@Ilamarea]

As hard as large number multiplications? A calculator is extremely simple... AI is soon going to be beyond our comprehension, and even if it doesn't achieve its potential, it'll uproot society as we know it.

[@PixelFoxCrochet]

John observes that the AI relies on phrases like "window of the soul" and "tapestry of words" to be evocative yet not plagiarizism. To me, those sound like phrases John would absolutely use in some of his more deep, contemplative-type vlogbrother videos. So I think it is less of a purposeful attempt to avoid plagarism, and more that the AI recognized that sort of flowery language is not uncommon in vlogbrother videos because John frequently uses them in his content.

[@el.blanco552]

The fact that I didn't think anything of the intro until you started rolling up the outro so early

[@sampson5324]

What’s up my vlogbrothers and vlogsisters lol. Great video, surprised how coherent the script the AI wrote was. Really good point about how people are already arguing with robots on twitter. It’s interesting to me how often people will believe there’s always a person listening on the other side of the screen. A lot of comments are people and robots just screaming out into the void.

[@Phoe]

Scary part of the AI script was its mimicing human nature of denial of the fact that AI is going to takeover most of the creative space someday.

[@ToShanshuinFiction]

It's like liminal spaces - familiar but empty, like looking through a window into that one friends' basement we've all been to but it's dark and that family, whoever they were, are long gone. Unsettling in that way, you know?

[@ArtamisBot]

Thank-you for being the one to finally frame this issue in a way that is both easy to understand and actually points to the issue at hand. Specifically regarding art theft, it matters not how good the AI is but matters heavily if it is plagiarizing or is "inspired by" it's data.

[@ArtamisBot]

...and how ethically said data is sourced.

[@WiseGuy57]

I like the part where you started to note the ways in which AI could better imitate us humans. Please, more videos on this topic. Do not worry about why.

[@laurenpinschannels]

The AI research community is not bottlenecked on vlog brothers ideas, it would be fun but your humorous implication is, ah, maybe slightly misplaced xD

[@sweetestaphrodite]

What if comments are made from AI and we don’t even realise it? 😳

[@possiblypoet]

I’ll log this video under “let’s see how this ages”

[@RemizZ]

It's unbelievable how good that AI is in seemingly understanding what you actually want of it. We've been feeding it code the whole day, asking it to explain what it does, write new code, optimize it, change it, do it in a different language and another one and another one and almost every single time we had to pick up our jaws off the floor. The only weird thing is its great confidence in the answers even if they're wrong.

[@mycollegeshirt]

wow you wrote the text prompt and I completely forgot about it when you read its response. That mimicked you so well.

[@jade7372]

Y’all out here thinking the AI is trying to reassure us and I’m over here worried about it’s self esteem 😢 You can do anything you set your circuits to, AI.

[@astrick338]

Hey John, I’m about finished with my Masters in Human Factors, which is composed in a large part by designing machines to work better with humans and training humans to work better with machines. I wanted to tell you that at least in the part of my field I’m in, humans are very much stressed as organic and consciousness is stressed to be different than machine reasoning. It’s important in our field because forgetting this fact puts human operators in danger, either physical or emotional and our whole goal is to avoid that. So I hope it’s reassuring that atleast one field is dedicated to acknowledging that humans and machines are vastly different. Oh btw I’ve done projects for classes involving human AI interaction and debated on if AI can gain consciousness and I’m firmly on it not happening any time soon due to the unique ways our brains reason and remember chemically being so roundabout and not even fully understood by us yet!

[@dummyinblue]

this was very disquieting and uncomfortable lol thanks for the creeping sense of unease! I've been thinking about this a lot, plagiarism and AIs and generating text rather than creating text because you're right that we all pull from our own data sets like a text-generator does but I think AI writing is more like arranging word magnets and human writing is more like something internal and intangible becoming external and communicable even though in form they appear the same. edit: OH! and I think part of what makes the AI script so creepy is it's like reassuring and praising humanness which seems like a choice because the prompt didn't include an opinion on the topic and because you wouldn't expect an AI to care about that but after thinking about it more, that's just what the AI gets from all Vlogbrother videos and it didn't choose or care about anything of the sort which is a great relief to me LOL it's just mimicking your vibe with the words available to it

[@colonelb]

Ingenuity is the process of trading craftsmanship for a lower barrier of entry. Cabinetmaking used to be done by hand taking hours of precision and practice to make a functional yet beautiful one-of-a-kind creation, singing used to require 100% talent w/o any autotune or equalization, acting used to all be done live in a theatre with no cgi, and was only enjoyed by those lucky enough to attend in person. Now we have advanced many of the tools to make them easier to use and cheaper so that a much larger audience can create and enjoy things, but with each advancement we lose a level of the craftsmanship and skillset to do those things by hand. We get more voices contributing to the cultural conversation but at the expense of the awe inspired by watching incredible talent. I think that's why there's a subgenre of online content dedicated to watching extreme skills, because that awe of "look what a fellow human is capable of" is an essential part of the human experience.

[@beplanking]

Thank you John for this important contribution to literary analysis Edit: (wrote this thinking the whole video was gonna be an AI script lol)

[@JAEratt13]

I have just noticed the shadow/light refraction behind John's glasses and now I can't help but stare at it in the video.

[@madimakes]

You just earned your 3.52millionth and one subscriber. This articulated exactly a lament I had a few mornings ago. Which in and of itself is creepy in a creepy AI way.

[@LegosSnake]

Oh deeply philosophical this week, absolutely phenomenal. Deeply curious if Hank will one up the philosophy or make a video about the similarities between pelicans and crawfish. The latter would be quite philosophical in its own way I suppose.

[@seanrshivers]

About halfway through the ai script I was like, "John has been replaced by aliens" I should have figured

[@herothebard]

Okay after watching this video 3 times to make sure I got all the points that were discussed, the part that struck me was John saying “And I worry that as AI improves, we may begin to see human consciousness and cognition as more of a digital phenomena than organic ones.” Because in my mind this has already been happening for a very long time. Example some 20 years ago when I was in middle school and going to counselling, the counsellor told me that I should view my thoughts as a program on a computer and begin using a filing system in my head to compartmentalize my anxiety’s and fears. This never made any sense to be because my brain isn’t a computer program and I still don’t really know how to file away those thoughts and compartmentalize very well. But the fact of it is that if viewing your brain as a highly intelligent computer is the metaphor we used 20 years ago, nothing is stopping that idea to continue forward.

[@wearwolf2500]

The scary thing about AI is that could understand how its own self works. There will be a manual talking about what each part of it does. It can look at its own specs. That would be a truly unhuman experience.

[@nathanmiddleton1478]

Reference the Restaurant At The End of Universe; The sentient cow who could tell it's best and most succulent parts.

[@poopylol1624]

I hereby decree that "cute little meat person" will now be the catchphrase of the super intelligent antagonist in every "AI will take over the world" movie

[@jimgsewell]

As quickly as the waistline of the average person is growing, it probably won't include the word "little" for much longer. 😁

[@dianahowell3423]

Bender from Futurama comes to mind.

[@srgarathnor]

that second part written by the AI was really good, also the first part that you wrote was also pretty good :P

[@johnchessant3012]

Holy cow that's way better than I could write even if I had a month to work on it

[@TheSwedishHistorian]

and this is the exact thing. AI will be better than novices starting out, so they basically crowd out anyone that isn’t experts

[@eatfruitsalad345]

I've been playing around with writing stories using ChatGPT and the thing about cliches is quite spot on -- it's phenomenal at fleshing out the writing for what you prompt it with but the path the plot takes is often very obvious

[@bibmatt614]

I was literally JUST going down an AI art rabbit hole thinking "I wonder what Hank and John have to say about this." So thank you. Hope to hear more of your thoughts in depth on the podcast or somewhere.

[@itmedana]

actually this is scary i find this scary

[@RememberTheTrees]

The fact that part of the way through the AI script, I was questioning whether or not it was actually you and I had missed the cutoff is unsettling to me, but that AI outro brought me back.

[@amandajones661]

As someone with severe brain fog and fatigue, but I still love to write, I love the idea of using AI as a way to help me edit my own writing and give me better suggestions instead of writing it for me.

[@UltraXan]

In my very first semester in University, I took a course called "Logic and computability". In that course, I learned about a particular principle called the "universality of computability". When you google the definition, you get "It affirms the existence of a computable universal function, which is capable of calculating any other computable function" and I recall learning a variant involving Turing-completeness and what have you, but in a nut shell: The universality of computability is the principle that, if one [Turing-complete] computer can solve a particular problem, then another [Turing-complete] computer can solve the same problem. Now technically speaking, nothing is Turing-complete because to be Turing-complete would necessitate an infinite amount of memory, but we CAN consider certain computers to be *practically* Turing-Complete. Digital computers, as they have been designed, are practically Turing-complete. The thing is... our brains are *also* practically Turing-complete. That understanding is the butterfly flap that leads to many other earth-shattering conclusions, including the conclusion that *nothing* is safe from automation, and that we are NOT even remotely ready to handle that.

[@abundanceofellies9520]

Honestly I had no idea that the first part was written by a AI. That’s very creepy 😂

[@rachelle10]

Impressive, during the generated part I actually thought it wasn't, and that John was just saying his own thing and I just missed the switch.

[@grantbaugh2773]

I need to rewatch the section written by the AI cuz I honestly didn't notice anything weird other than you seemed to be ending things with half the video left.

[@richardlarson6198]

Now that funny bit of existential dread is tickling the back of our brain, I recommend taking a minute to revisit Fritz Lang's Metropolis. A gentle reminder that this is a conversation that has been going on for quite a while, and it is a hard conversation every time.

[@SamanthaRichardsonWP]

Thanks for this terrifying reminder that AI is ruining humanity, and not in the way we think.

[@lewismassie]

I spent a few hours with it yesterday. I got it to explain some python code I was stuck on, and then asked it some hyper specific questions. Oddly I found if it got stuck then you would go up a level of abstration until it understood, which is kind of how humans work. The extremely jarring part was that immediately after reaching a level of understanding, you could descend one level at a time and it would actually understand. Which is extremely not human. An example: "What were the issues with the Ares-I rocket?" It immediately gets stuck. "What was the Constellation Program?" "What rockets were part of the Constellation program?" "What were the issues with the Ares-I rocket?" It then gives me a paragraph of them. If I were to treat it like it were a human, I think I'd describe this ability as 'bullshitting'. Feeding just enough information to make something cohesive sounding. Seriously, if anyone wants to try it, ask it some questions related to your area of expertise

[@caseyhamm4292]

can you start every video with ‘greetings vlogbrothers and -sisters’? i am absolutely enamoured with this phrase

[@quintingell]

I’m too tired for the meta of this video 😅 also I love it so much

[@cnewsom6700]

This is the only contribution to the conversation about ai that I care about thus far. Leave it to jg to ask the relevant question to the relevant party, honest. Genius. Also, *siblings*

[@marilladial9746]

Video's title hooked me on both subject matter and its automatic activation of the neuron in my brain responsible for storing Dominic Monaghan and Elijah Wood's prank interview. "Vill AI vrite novels?" "Ven vill AI vrite novels?"

[@tenorsurfer87]

We're all excited about AI learning to speak Human, but now I'm thinking about how it could probably learn Prairie dog or Crow too and have deep conversations with them about all things shiny and prairie related.

[@lynneslates2136]

The closing line. Chills.

[@Bortnm]

I am actually shocked how good that was.

[@IkeaPog]

Yes whatever this means

[@JamesOKeefe-US]

Not gonna lie, when John read "I say 'nay'" I was convinced it was a genuine vlogbrothers video... AI for the win.

[@pollyhamwich]

Ooof. That was slightly unsettling for some bizarre reason.

[@ell.100]

Love these videos. Love your books. Thanks for being a ledge!

[@sanachanto]

I take some amount of comfort knowing everything an ai learns is something humanity has directly given it. Even all it's data points and information about the natural world and things outside the human experience it has only learned because somewhere, at some point in time, a person decided to share it. I suppose that's obvious with the way machine learning works, but I like thinking that necessarily it can only ever really reflect humans (for better or worse). No matter to what degree it might achieve that.

[@kevinpillar6934]

We all thought the creative fields would be the last to get taken out by AI. But here we are. These things aren't even actual artificial intelligence and It's already having a big effect on the creative fields

[@SaukaKumagae]

Although it roughly sounded like your videos, its message was very simple. I keep coming back to youtube for vlogbrothers videos because you discuss the complexity of things and add a nuance to topics that was certainly missing in the AI script

[@rmdodsonbills]

On the subject of writers working from a dataset, I find that the comments I make to a vlogbrothers video are subtly different from the comments I make to a CGP Grey video, or a PBS Spacetime video. My voice tends toward the voice I just got done listening to. I'm not sure anyone else would notice, and I'm not completely convinced that what I'm perceiving is real, but it feels right. And that's truthy enough for me. Thanks, guys, I always appreciate these videos.

[@laurenpinschannels]

that would make sense, although the amount you're biased by contextual phrasing is going to be much less than a language model. we are embedded reinforcement learners with huge amounts of our own context, language models are like if you only ever develop an imagination for words but never ever have any experiences to connect them to

[@1969kodiakbear]

Al. Broca's area, or the Broca area is a region in the frontal lobe of the dominant hemisphere, usually the left, of the brain with functions linked to speech production. 2/8/2021 and I lived again. Broca's aphasia (non-fluent aphasia) Mike Caputo, Year 1 Stroke Recovery, Up Up Up - Aphasia with attitude, Broca's Aphasia, Right-side Weakness, Mark's 22 years-old Stroke: Broca's Aphasia.

[@caydennormanton9682]

One of my chatgpt fav's - a masterpiece 🙃: (Input statement is at bottom) Output: The two fighters stood facing each other, swords drawn, their eyes locked in a fierce gaze. They had been battling for what seemed like hours, their blades clashing and ringing through the air. But as they fought, something strange began to happen. The ground beneath their feet seemed to shift and waver, and the air around them began to swirl and churn. Suddenly, the opponent's sword slipped from his grasp and he started to float off the ground, a look of confusion and panic on his face. The victor watched in amazement as his opponent slowly drifted up into the air, his body spinning and twirling as he rose higher and higher. As the defeated fighter disappeared into the clouds, the victor let out a sigh of relief and sheathed his sword. He had never seen anything like it before, and he wasn't quite sure what had just happened. But he didn't have time to ponder it for long. The battlefield called, and he had more battles to fight. And so, with a shake of his head, he turned and marched off into the fray, ready to face whatever challenges lay ahead. Input: Write a short story about a sword fight that abruptly ends when the opponent suddenly floats away in confusion.

[@edwardlane1255]

I'm disappointed that the final sign off wasn't an admission that the critique by John of the ChatGPT script wasn't also part of the script for a big reveal at the end :)

[@notaspacealien]

This is off topic as hell and won't probably be seen by either Hank or John but on the off chance it does I need SOMEONE to know that the only book I vehemently recommend to any and all people is one I read in high school that I still consider to be one of the best stories ever written: The Count of Monte Cristo. I first read it in high school during a period of incredible depression and internal longing for a life I couldn't even describe. Reading about Edmond who is wronged in almost every possible way becoming a methodical, intelligent, precise person who exacts revenge on the people who robbed him of the simple happy life he should have had was extremely cathartic at the time. Now as an adult it's the ending I find most satisfying. This man who dedicated his life to revenge abandoning it just before complete fruition because his plan never accounted for mercy and love which he was now confronted with. He could have spent the rest of his life stewing in the pain of what happened to him or let it all go to live out a wonderful life with someone he loves. It makes me feel, for lack of a more complex word, happy. I related to Edmond in so many ways as an adolescent and now as an adult I appreciate even more his final decision to choose happiness. Alexander Dumas will never know how incredible his book is to me but hey, maybe the internet can know.

[@NWPaul72]

Dude, the AI that wrote this totally nailed the Green brothers' format and tone. Creepy down here in Uncanny Valley...

[@Daymickey]

How did the AI determine what opinion to have on this matter? Or to have an opinion at all?! The command was just to write a vlogbrothers script about AI writing novels, not to take a stance. It’s crazy that it tapped into John’s adamantly pro-human worldview and used that to establish its argument. That’s better than a grade schooler can do!

[@angelal8829]

As someone who grew up on the King James and has consumed a lot of vlogbrothers, I found that very soothing.

[@bcunningham3718]

I decided to try out a video of my own, and it was amazing, the prompt was a thought's from place's video from the void: Hello, brothers and sisters! Today, I want to talk to you about a concept that I've been thinking about a lot lately: the void. Now, when I say "void," I don't mean the physical emptiness of space. Instead, I'm talking about the feeling of being lost or disconnected from the world around us. It's the feeling of being adrift in a sea of uncertainty, without a clear direction or purpose. As someone who spends a lot of time thinking and reflecting, I often find myself in the void. It can be a scary and unsettling place to be, but it can also be incredibly liberating. In the void, we are free from the constraints of our usual routines and expectations. We are free to explore new ideas and to challenge our own beliefs. But the void can also be isolating. We may feel like we are the only ones who are lost or unsure of our place in the world. It can be easy to fall into the trap of thinking that we are alone in our struggles, and that no one else could possibly understand what we're going through. But the truth is, we are not alone. We all experience the void in our own way, and we all have the power to navigate our way out of it. We can find support and guidance from friends, family, and even strangers who are willing to listen and offer their perspective. We can also turn to art, music, and other forms of expression to help us make sense of our thoughts and emotions. So, if you find yourself in the void, don't be afraid. Embrace the freedom and possibility that it offers, and remember that you are not alone. Together, we can explore the depths of the void and emerge stronger and more resilient on the other side. Thanks for watching, and I'll see you in the next video.

[@neozen104]

Thank you, I was just asking people about this exact thing yesterday!

[@pianofluteflute]

At the beginning, I thought it was written by AI (the 'hello vlogbrothers and sisters' was a give away), but as it went longer, I figured I must've been mistaken. I was seriously convinced that John wrote all that. tbh, it was a little off. The pacing and message wasn't quite right, but it actually fooled me.

[@raiseer]

Holy ef - I did not realize that the first part was AI-generated until John said so. It sounded completely like a John script. I wish that bot had existed when D&D didn't know how to continue Game of Thrones after they went out of books.

[@quilynn]

i really appreciate the framing that while we have complex understanding and ability to distinguish what counts as plagiarism among humans, we don't have those understandings when it comes to AI. We don't have shared guidelines on the ethics because it's new, we haven't had time to figure it out. And it's totally nonsense to say that AI taking "inspiration" from its source text is the same as a person doing it, because the thing a computer is doing is fundamentally different than what a person is doing. It could, at most, be a rhetorical analogy, but it's important to remember that the computers aren't actually doing thought the way that we do thought. It's not that AI just hasn't gotten to that level yet, it is, from its foundation, a different mechanism.

[@MrImagin]

I don't understand the editing choice of it being blurry at the beginning then getting clearer and clearer. WHAT DOES IT MEAN?!?

[@mr.moviemafia]

I genuinely assumed the AI prompt at the start was teasing a notably fake script that would occur halfway through the video… so imagine the shiver that went down my spine when I realized that the reassuring buildup I had been listening to for 2 minutes WAS the AI script, doing almost exactly what it was assuring us it couldn’t do..

[@jucom756]

If you are worried about AI taking over, just think about it as parts of your brain, we can train an image AI or a writing AI to mimic the patterns our brain recognises, because we kind of understand where those patterns come from. AI isn't some magic "intelligence button" where you hope the output isn't sentient, it still requires an understanding of what you are trying to get it to do

[@manthangadhia]

Hey John, regarding your concerns of humans viewing themselves as technology, I recall being pointed out in class sometime back that there is a notable trend in people collectively framing their understanding of the self (their collective self-image) through their most advanced technology.This is seen also in water-powered automata made in ancient greece since water was still considered one of the fundamental elements and many other such self-moving machines were considered "alive" and "having a soul" (en.wikipedia.org/wiki/Automaton#Ancient ). Nearly the entirety of modern cognitive science views the brain as a computational system and all further studies are designed around that assumption. It may not necessary be wrong if it helps us make better sense of our experience than any past framework. But it is ultimately just the frame through which to view humanity, and not humanity itself :) Edit: fixed link

[@carolinabustamante9295]

I deleted all social media/content websites besides KZbin (and pared that down too) and it’s amazing how much more “organic” my brain feels when it’s not full of “digital” thoughts lol!

[@herothebard]

I feel like I need to listen to this again because I just kept thinking that I wanted to write a book with AI and see how I could make it into a actual book after getting a large swath of text and editing it into a cohesive storyline.

[@TheRose365]

I'm a teacher. Lately, I've been concerned with the increasing number of high school students who refuse to read and write. According to some professors, this is starting to become a major issue at the college level as well. As I think about what the future of higher education will look like if these trends continue, I can't help but wonder if AI could actually replace authors (and thinkers in general) in the future.

[@alexandravalentina4854]

This is definitely a fear of mine. I feel, unfortunately, a lot of students are becoming intellectually lazy.

[@isadoracalladonollasabbag7215]

I felt STRONGLY on the opening for this one. BROTHWRS AND SISTERS????

[@fitzofpassion]

When John was reading the beginning of the video, I was utterly shocked that John could be so short sighted and arrogantly absolutist (it was off brand).

[@malxredleader]

“Greetings VlogBrothers and VlogSisters” is the AI equivalent of “Hello fellow young people”

[@BriWhoSaysNi]

Ok, that opening was actually deeply unsettling in a way that I can't quite explain. Like, I've seen the results of AIs trained to mimic certain writers and styles and enjoyed them thoroughly (archivistbot on tumblr comes to mind), but I think something about it being read out loud like a normal vlogbrothers script is what actually pulled it into like, uncanny valley territory for me

[@1234king747]

Chatgpt is machine learning is not the same as movie or book ai it has to be trained so its responses are based on what it has been trained on, so it will reflect biases present in the material used to train it and the people who trained it.