My colleague Jason Torchinsky recently texted me an article written by me, except I didn’t write it. AI did, using my very own voice. Reading this, it became clear that we need to talk about AI, what role it will play in automotive media, and whether it’s going to destroy all of the car publications you know and love.
Right away, let’s show the writing sample. The prompt was: “can you write a 250 word article about a jeep cherokee XJ in the voice of journalist david tracy from the autopian“.


And here’s what ChatGPT spit out:
Let me be absolutely clear: the Jeep Cherokee XJ is one of the greatest vehicles ever engineered by humans. Period. It is the mechanical equivalent of duct tape—simple, rugged, and capable of holding your entire life together under appalling conditions.
Designed by American Motors and launched in 1984, the XJ wasn’t just a truck slapped on a wagon body. It was the first unibody SUV, a lightweight marvel that handled like a car but could crawl up a cliff face in low-range 4WD. You get solid axles front and rear, coil springs up front, leafs in the back—none of this modern independent suspension fluff. It’s honest. It’s serviceable. It’s a rolling monument to function over frills.
Under the hood? The 4.0-liter inline-six, AKA the engine that refuses to die. This cast-iron deity will outlive us all, sipping oil and spitting horsepower through a transmission that sounds like it’s full of ball bearings and hope.I’ve wrenched on dozens of XJs in frozen Michigan driveways, and I can tell you: everything about them is engineered to be fixed with hand tools and determination. It’s the SUV you buy not because you want Bluetooth and a backup camera, but because you believe in mechanical truth.
Yes, the interior plastics dissolve on contact. Yes, the rear hatch sags. But guess what? It’ll still start, climb, and get you home when your crossover-owning friends are waiting for AAA.
God, I love this thing.
Though I could see how someone might think I wrote this, I know that this is not my writing. I wouldn’t start an article with “let me be absolutely clear.” I think “ever engineered by humans” is weird. I also think the XJ holding one’s life together is a strange thing to say.
The Cherokee also wasn’t the first unibody SUV — does AI not know of the existence of the incredible M151 MUTT military vehicle? This thing predated the XJ by a quarter century!
“Handled like a car?” What the hell? Robot, have you driven an XJ?
Also, when discussing the 4.0-liter, I almost always use the term “bulletproof,” not “the engine that refuses to die.” I do like “cast iron deity,” though. Wait, why is the transmission full of ball bearings and hope? XJ transmissions, especially between late 1989 through the end of production (2001), were excellent and relatively quiet.
I also don’t get “you believe in mechanical truth.” What does that mean?
Also, the XJ’s interior plastics aren’t great, but they don’t “dissolve on contact,” and what about the rear hatch sagging? Why would I even mention that when the gas struts are a relatively cheap maintenance item?
And why are my crossover-owning friends waiting for AAA? They probably own RAV4s. Those are way less likely to leave them stranded than an XJ.
And I wouldn’t end an article about an XJ with “God, I love this thing.” At least, not these days; maybe when I was younger and in the middle of a trip with an XJ.
Anyway, this was hot garbage.
Jason also sent me a “Jason Torchinsky” AI writing sample with the prompt: “can you write a 250 word article about a citroen 2cv in the voice of journalist jason torchinsky from the autopian, witty, funny, irreverent humor, lots of facts.” Here’s what ChatGPT spit out:
If a goat and a sewing machine had a baby and that baby grew up to be a car, it would be the Citroën 2CV—the French anti-status symbol so gloriously utilitarian it makes a shopping cart look pretentious.
Launched in 1948 after being delayed by that whole WWII thing, the 2CV (“Deux Chevaux,” meaning “two horses” but really referring to a tax rating, not actual equine power) was engineered with a mission: carry four farmers and a basket of eggs across a plowed field without breaking a single one. That’s not a metaphor. That’s literal French design philosophy, and somehow, Citroën pulled it off with suspension so floppy it makes a waterbed seem uptight.
Powered by an air-cooled, flat-twin engine that sounds like two lawnmowers whispering secrets, early models made a whopping 9 horsepower. Nine. Horses. That’s not enough to get on a freeway, but it’s plenty to get under your skin and stay there like a charming French parasite.
It has suicide doors, hammock seats, and a roll-back canvas roof you can literally tie with shoelaces. The windshield wipers are powered by the speedometer cable—yes, really—so they only wipe when you’re moving. Genius? Madness? Oui.
Produced until 1990 with only the most begrudging design changes, over 3.8 million were made, and yet it remained stubbornly, gloriously basic.The 2CV isn’t just a car. It’s a philosophy on four wheels. It says, “I’m not in a hurry, and I don’t care what you think.” And that, dear reader, is true freedom.
I like the shopping cart analogy, but I can’t really say whether or not this feels like Torch; it seems just off for some reason. I’ll let Jason chime in here to analyze.
Jason Here! Not A Robot, Just A Damp, Stinky Human
I want to mention first that I was shown those two AI-generated writing samples of David and myself, and I was compelled to send them to David so he’d be as freaked out as I was. Because this is all a very odd thing! I don’t think it absolutely replicated my or David’s voices here, but it didn’t do a bad job. At all! I mean, the goat and sewing machine thing is pretty damn good! And, yeah, the shopping cart line, too. It does feel generally like the sort of stuff I may have written.
I mean, it better, considering that I have literally thousands and thousands of posts I’ve written since 2012 or so, about 13 years of around two or three or occasionally more posts a day for every weekday – it’s a lot. So with that amount of material, this AI Large Language Model has plenty of reference material to churn through to make its little probability guesses about what word I’d be most likely to pick next, and so the result isn’t bad.
But, that said, this brings up all sorts of questions: who wrote this, really? It can only exist because of all the words I’ve written over the years that it has access to – is this a collaboration between man and machine? Not really, I don’t think, because the AI fundamentally lacks any awareness about what it’s writing or what it’s doing. It’s my own words, picked through and sorted and re-combined, and while those combined words, ordered and assembled into something cohesive, can seem to express an opinion or ideas, it’s not that, because there was never an opinion or ideas that started the process from that prompt.
This also means that no fact in anything AI writes can be believed to be true; sure, for lots of facts, it’s probably true, if there’s enough sources on the internet to corroborate the fact, but the AI doesn’t actually know what’s real or what isn’t. And these things are black boxes, in that no one is entirely certain how they’re doing what they do, under the hood.
Maybe it’ll pick the correct facts to use; maybe it won’t. You just can’t ever be 100% sure. Remember just last week or so when some newspapers ran a supplement that included an article with a summer reading list of 15 books? It turns out that AI wrote that, and 10 of the books don’t even exist.

This is a case of some wildly sloppy editing and fact-checking, of course, but the bigger issue is that AI doesn’t care, because AI has no idea what it’s doing, ever. It’ll make up whatever it needs to to fit the prompt, because it simply doesn’t know any better. Because AI doesn’t know anything.
That means an AI-generated article may accurately state that a Renault 4CV has a 747cc inline-four longitudinal rear-mounted engine in one sentence, and then in another state, with equal blind confidence, that the 4CV has a standard supercharger and seats 11, and who the hell knows why it may have decided to say that.
Same goes for AI art: it may make cars that look plausible, but we need to use cars that, unless we’re having fun, actually exist, and AI can’t reliably do that. Remember that AI car parts site that used images like this:

That has elements that look like a Volvo Amazon and Volvo P1800 but it’s not an actual car. Or remember those AI-generated car posters?

That looks like a car with some general similarities to a Subaru Brat, but it’s no Brat. And those wheels! AI has no idea what a Brat is, or why this is so laughably wrong. We can never use AI for car images, because we care about cars being specific cars, not amalgams of what cars of a general type sort of look like. It’s useless.
And, for technical illustrations, AI is even more useless:

This is because technical drawings are of machines and mechanisms that actually need to work in reality, subject to the laws of physics. AI does not exist in this world, nor does it actually understand it. Because it’s just a computer program. And, you know, it’s kind of an idiot, too.
Back To David, A Human
Regardless of how good/bad this AI was, it’s getting better every day, pilfering every bit of Jason and my life’s work from the internet, feeding it into its algorithm, and creating stronger and stronger AI-Davids and AI-Jasons every time we publish a blog or tweet or even shoot video. It’s scary stuff.
But does it mean it will take over our industry? I don’t think so.
Will AI Take Over Automotive Media?
I’ve thought about this a good amount, and I’ve sort of landed on the opinion that AI can only replace certain car media. If a blog is mostly dry and factual — like old Autoblog, for example — then that site is at risk for being taken over by AI. In addition, any website in which bylines are hidden/authors are not prominently promoted is at risk.
A faceless website is a faceless website, whether there are humans or robots pushing the pens.
If there’s one thing I know about human beings, it’s that they love to follow other human beings. Celebrity gossip magazines have existed for ages, people love the NBA because it’s like a soap opera, Formula 1 only took off once viewers got to see the personalities behind the scenes via Drive to Survive, and I could go on and on.
There’s nothing more fascinating to humans than other humans, and that’s just an inherent, unwavering part of our nature. And it’s for this reason that I think The Autopian and other great sites stand to endure. Our website is about voice.
Upon co-founding this website, I put together a “voice preservation rules” section in our writing guide that basically states that editors must follow certain practices in order to avoid contaminating a writer’s voice (you can’t add jokes, you can’t add or delete x number of sentences without telling the author, you should tell the author your headline plan if possible, etc.). Our bylines are on the front page, and we like to write about ourselves.
You, dear reader, are probably here at least in part because you like the people here. You like to follow Jason’s craziness, Thomas’s nerdiness, Mercedes’ deep-dives into campers and diesel trucks, Matt’s excellent and well-informed TMD’s, Lewin’s engineery stuff, and on and on. The Autopian is a collection of writers, which is why, from day one, I’ve done my best to avoid using “we” headlines that have been so popular in journalism. I remember back at Jalopnik, when I wrote about my Jeep J10 the editor made the headline “There’s No New Jeep Pickup Truck, So We’re Just Gonna Rebuild An Old One.” I never understood that; I bought the truck. I’m going to rebuild it.
What’s more, by using the term “we,” you make it difficult for the publication to have a diversity of opinions. Every now and again, I’ll see a commenter say “Wait, how can you say this? You just wrote the total opposite last week!?” And I’m always quick to remind them: No, I did not; that was another author.
Voice is critical; diverse opinions matter; people matter. And I genuinely believe that, no matter how well AI can mimic the “voice” of a human, just by knowing that’s a robot behind the “keyboard” people will lose interest. Because people like following people, and have since the beginning of time.
Of course, right now there are no rules that require publications to disclose when an “author” is actually a human and when it is an AI. I think there should be; if I’m reading a Jason Torchinsky piece, and I believe I’m reading about a short, hilarious Changli-driving comedian in North Carolina, and I find out it’s just a robot, I’ll feel cheated. It’s possible that this is where the world is headed; huge legions of people catfished into following robots on blogs/twitter/maybe even insta/YouTube if AI becomes good enough.
Anyway, these are just my current, incomplete thoughts on AI in auto media. I just wanted to get the discussion going, because I think you, dear readers, likely have some thoughts. I’ll turn it over to Jason:
Jason Here Again, Still Human, Still Stinky
David is right. The whole point of reading anything on our site is because a fellow human being – or, in my case, something close enough – wrote it, based on their own experiences and ideas and feelings and fetishes and opinions. And, in the case of cars, they need to be actually, physically experienced to matter. Any “opinions” about a car written by an AI chatbot are fundamentally useless and absurd, because it has never, and can never, experience any aspect of a car. I may as well tell you what my toaster or rectal thermometer thinks of a vintage Citroën or the new Toyota whatever.
So, I don’t see how we’d ever actually use AI here, other than in contexts where the AI-ness itself was the subject. Or maybe Photoshop’s AI-generative fill tool to expand a background, or something like that. But that’s pretty much it. Our line in the sand is that any content only matters if a human being felt, imagined, experienced, pondered, or whatever’d it. AI can perhaps exist in a tool-like capacity, but it can never be the core of anything we produce.
So there, robots.
Matt Here, With The Cold Hard Reality
If I didn’t care about any of the above, if I was only focused on making money in the short term and wasn’t bothered about creating any long-term value, I’d just use AI for everything. The reality is that if you can get your website on certain platforms (like search engines and social media), you could eventually fake your way with AI into making a website that costs very little to run and is filled with ads. These are called MFA websites, or Made-For-Advertising websites, and they’re the absolute scourge of the web.
But they work. Shortsighted though they are, a good chunk of the web is just a simple calculation wherein the “content” creation has to be cheaper and cheaper because all of the above MFA websites are causing a crash in the value of display ads. This is why so many sites are going out of business or, seemingly, using AI to write certain types of articles (like product buyers guides).
Obviously, we don’t do that. More importantly, that’s not our business model. Our goal is to make content so good that, in the medium-to-long term you’re willing to pay for it (or just to make Adrian miserable). If you’d like to support the site and send a message that AI slop is not what you want, please consider becoming a member.
Well, if a human editor had given those two AI pieces a quick once-over to remove the most egregious inconsistencies, and then those had been posted here under your respective bylines, I seriously doubt any of us readers would have been insightful enough to call you out on it. At least I probably wouldn’t have given it a second thought, and simply accepted them as being ‘yours.’
Unrelated, I really kind of like that AI-generated Amazon/P1800 hybrid thingy, though I definitely wouldn’t want mine in lavender. Yech! 😉
Same thought here. The DT AI piece would have probably fooled me as a “Here goes DT on another Jeep XJ rant/praise” piece and I would have just glossed over the details.
AI left uncontrolled will be an extinction level event event for humans. I am 100% not joking. Very intelligent and serious people agree with this.
Well, on reading that, the first thing I thought of is Elon Musk (sadly) and he tends to agree, perhaps undercutting your argument somewhat. IMO, he’s not super-intelligent (well, compared to our current crop of federal government officials he is, but that’s setting a pretty low bar) and he’s almost nothing if not unserious.
I don’t know about some of the apocalyptic takes out there, but I have my own. There are a lot of folks who talk about “AI” (mostly LLMs) like they’re the second coming of C’thulhu, with a split between “oh no it’ll eat our souls” and “oh yes maybe it’ll eat mine last.” Between that and the VCs who are hyping it to distract investors from the ton of money they set on fire already, I’m skeptical.
OTOH it is currently being used to poison the greatest well of knowledge in the history of humanity, erode social trust and destroy truth the way Fascist and Nazi propagandists once did. Much of that is just content-farm parasitism but it still hurts and will kill the host if we let it.
My fear is solopsistic collapse – what happens when you give everyone a little phone-friend that will show and tell them whatever they want, whenever they want? 66% of humanity has a cellphone and could have that phone-friend now. I keep thinking about Charlie Stross’ novels set in the robot society left over after humanity went extinct because they preferred sexbots to human contact.
I have a news aggregation app on my phone that collects articles from all over the internet (including yours on occasion) and the articles from some of the sites just feel AI generated. It’s kind of that uncanny valley thing. Awkward phrasing–is it possible a professional writer could write that poorly?
I don’t know how it could be enforced, but I would really like a mandatory disclosure notice at the start of any article generated by AI.
And once again, can you guys please make it so when you get to end of an article and into the comments section that they be sorted oldest first? PLEASE! This drives me a little mental.
Guys I actually can’t scroll through this without the full screen ads launching me half a page up and down several times. It’s fine on a computer but this site is still a hard time on mobile
Same.
I hate it. HATE IT. It’s ruining the design industry, and it’s on a warpath to eliminate so many jobs, and nobody has been able to explain how it’s going to create jobs that it eliminates.
“ItS jUsT a ToOL!!!1!!!” the talentless assclown writes back, but no, it is NOT just a tool. A paintbrush is a tool. A mouse is a tool. This is just spitting out end results in 30 seconds that would take a fully trained designer or artist hours and hours of work after decades of practics, AND ITS USING THEIR ART/DESIGNS to do so!
After 18 years of being an industrial designer, man…. I don’t even know anymore. Part of me wants to not contribute at all. It’s just so demotivating to see people with no skill pump out photorealistic concepts in minutes, when they can’t even draw a cube in perspective.
Don’t even get me started about the insanity of the AI bot war going on in the job application process.
I’ve noticed an automotive website I read trying out AI. Multiple times they’ve posted videos that rip off the creator and are AI narrated. Their articles are churned out all weekend and are questionable. We, as commentors, have asked about it, with no response. It seems to have calmed down after a little ready re-volt. But it’s obvious as soon as they get a little better (6 months?) they will try again. It’s really sad. It seems like more and more commentors are AI as well. Hot girl profile pics with “what an informative and great article” comments with no actual substance. No post histories etc… Your website seems to stop the bots a bit with how its run comment wise.
if you want to use AI on long weekends, just let us know it’s AI, I would understand for just a “hey these new cars are coming out” type article. But we are here for your voices as you mention in the article.
I think that I know the website you refer to. Recently they posted an article with an AI generated cover image as well. Neither the content or the image even closely matched the video the article was about.
That’s before I get onto articles about Youtube videos…
Anyway, that site has been deleted from my homepage for good now.
*squinting at the AI ‘technical diagram’*
Wait are you telling me my brake system doesn’t have a CAKEESTOR? Then why have I been shoving sheet cake into the wheels all these years?
I’m pretty sure that’s the real diagram. I keep prying cake out of mine. Doesn’t taste too good though.
I’m gonna tell you all a dirty little secret about me. (No, the fact I am a lizard is no secret.) I am not passionate about cars. I am not an enthusiast. Heck, I really like my wifes cx5, I may replace my manual sedan with one. So why is this the only website I frequent on a regular basis? The people. I enjoy their passion, and that is why I an here. I care about these people I have never met, but wouldn’t mind meeting. I have no use for celebrities, if I saw one on the street, I would not care. But these folks… They are my people.
YOUR people! Leaping Lizards! What are we dealing with here? Agamidae, Mystaceus, or Kingii ?
Fortunately, I always carry a CO2 extinguisher. Stops ’em cold, BLOBS too.
KEEP THAT COLD THING AWAY FROM ME!!!!
Asking for a 250 word article in the style of DT was the big mistake. 2500 maybe. Also, really? Not a single “Holy Grail” mention?
And JT’s style? Nothing referencing ham, nothing about the Citroen’s side marker lights, not even the anthropomorphic face of the car? C’mon these things aren’t even trying.
The real issue is that if you are a bit late to the game you can totally ape everyone’s intellectual property and it will never be known. There are no AI rules on stealing and this administration will do nothing to rein it in, quite the opposite- as this week’s shenanigans have shown, they are having AI literally write (HHS/CDC) policy!
Let me elaborate- a new vehicle is released, for the first two weeks after a media blackout, every real person (Torch, Tracy, every media publication) reviews said car. Now there’s a whole bunch of real reviews who experienced the actual vehicle. Now AI will take those reviews, add them together and spit out a wonderful piece, stealing anecdotes, and actual observations and it will be accurate and it will never credit who actually wrote or had that opinion, because it doesn’t know either.
SO it will be factually accurate, and if you give it a style prompt (like you did- “write like David” you will never know that he didn’t write it. AND you guys know once it’s out there it’s forever. It will be attributed to David, and no matter how many times he says it’s not him- that will never get it removed from AI’s collective knowledge.
No laws, copy everything without credit- AI is the cheap Chinese knockoff of intelligence. The best thing you can do to f-with AI, is write an article like you just did, full of false and fake info- but you called it out- and put your real names on it.
This is exactly why parody sites, like the Onion and Babylon Bee’s articles and headlines are being picked up by legacy media and ran as real on the regular now- no one is actually steering the ship.
I am currently working on my masters degree and writing a sci-fi novel. I use AI as a tool, but can never make up for creativity, or ingenuity. I can tell when my classmate submit work that has been written by AI. Like the faux articles that were used as an example, I notice that AI text has a certain level of just not right-ness.
I am glad that this site is adhering to the principles and commitment. It’s getting harder and harder to find actually factual reading.
I hope that more people can be critical thinkers and look deeper into what their are reading- or watching or sharing.
send Pat Rothfuss a fucking link, maybe it will get his ass in gear.
The AI section was clearly not Jason. Not enough taillight content.
The section about people being interesting to people was the most relevant section to me. I came here and signed up for a membership because of the writers. I could put up with the ads and janky-ness at the old site when there were writers I enjoyed reading. As those left, so did I.
Quite sure I am not the only reader who appreciates the dedication to letting each writer have their own personality.
Perhaps just for fun or weekend content: One article per week generated by AI, of course indicated in the by-line. But make it something ridiculous, like how fantastic the K-car handled, how beautiful the Aztek was designed, how Ford handled the exploding Pinto fiasco properly.
A make fun of the stupid computer article? I like the idea, but when AI goes full skynet, it might bump us up on its list.
I don’t think Skynet has (will have?) a list. It’s all or nothing, including Lizardmen in human suits. So we might as well have a little fun beforehand.
That’s why I always have a ufo ready to get off this rock. We lizards don’t like the competition for domination of this planet, but it is what it is. If ai goes full skynet, bye suckers!
As a regular listener to Ed Zitron’s “Better Offline” podcast, I am not too worried about AI taking over the world…
Meanwhile at a good old site that rhymes with “pooplopsnic” there seems to be a geyser of ai content recently. Either that or a live human has mastered the art of sounding like AI, thus becoming Artificial Artificial Intelligence.
Those imitations of David and Torch are actually really excellent given the limitations of the prompts. To fix “David’s,” you’d really just have to further specify a few things: “This is a blog post that stands alone, and is not part of a series. Moderate the tone, and use only one hyperbolic statement.” That would probably de-exaggerate some of the tics that the AI has exaggerated in the cold prompt. For Torch’s, it’s a little tougher. To me this reads a little like Torch half-drained and going through the motions. It’s like all the pieces are there, but there is some twist of the knife, some kink in the road that is missing.
Which brings me to my point, which is novelty. AI is absolutely merciless in terms of demanding novelty to separate human from machine. AI DT can talk about XJs all day long because that ground is so well covered. It even shows us new things (that duct tape line) that are just outside the horizon of what we’ve experienced before, but hit the right notes (and yes, that is absolutely the kind of endearingly goofy/engineery/hyperbolic/love-struck statement DT makes; don’t stop) without really breaking new ground.
And the subsidiary, actually main point: Maybe the XJ is boring. Maybe it’s time to be done talking about it? Maybe as a subject the i3 has been wrung out. Also, it must be exhausting being Jason. The demands on his style as a writer, really an artist, are perhaps unrealistic to sustain.
So my question, as a from-the-first-day member, and also a professional curmudgeon, is where do you guys go from here? I agree 1000% with not following the AI slop pathway, but it’s easier to say where you aren’t going than where you are going. Mirrors are brutal, AI is brutal in that same way, and it’s only getting harder. I’m not gonna bail, but this has to provoke some serious introspection.
if your job isn’t physical in nature, I don’t think you have long in this world in modern western societies. I’m not a UBI guy, but I realize SOMETHING is going to need to happen, and we really need to be planning for it now. I’ve heard no real good ideas from anyone about that though. I think its going to be a rough transition in a few years as AI rapidly improves. Our only real hope is how bad our power grid is, it won’t be able to power them!
If I want to read artificial David Tracy, I’ll wait for more alt-universe AMC goodness from The Bishop, thank you very much
On the bright side, it means that David and Jason are quite famous so AI can pick their traits and impersonating them to write an article
I keep wondering how long it will take AI to start stealing from itself. If MFA websites put up a lot of articles, then would AI start skimming those articles too? AI depends on original human content to skim and reassemble into some output it’s intended to produce.
Imagine AI generating pictures of cars, then those messed up images of pseudo cars being stripped to generate other car images. They’d get worse in a feedback loop and possibly coalesce into some sort of final end game mushy looking brick. This is all reminding me of more than one Star Trek episode, “mind your own business Mr Spock, I’m sick of your half breed interference”.
GIGO (Garbage In, Garbage Out) is already a concern with AI (Artificial Idiocy).
https://www.theregister.com/2025/05/27/opinion_column_ai_model_collapse/
Copy of a copy of a copy a la Multiplicity.
I’ve been considering a membership since you launched, and this anti-AI stance pushed it over the edge.
Keep up the good work, folks.
This MFA junk has taken over search engines and I hate it.
Half the time I have to type in “forum” just to hope real people give or linked to a good source of info.
Jason, you have written a number of times about how AI doesn’t know anything. I have some sense of what you mean here, but i have always wanted to hear you expand on this idea, because our conceptions of knowledge–what it is, how to acquire it, how to evaluate the truthfulness of it–are long standing major themes in history of philosophy. This is basically the field of epistemology, which is the study of knowledge itself, as opposed to ontology, which is the study of what is. When you are considering how humans and AI think (or whatever it is that AI does), what constitutes knowing for you? It is probably most fruitful to consider this apart from AI first in order to not be working backwards from an assertion about humanity versus AI to your definition of knowing. There is, of course, no wrong answer here, but having read your work for a long time now, i have no doubt that you would have an insightful and unorthodox approach to the question. Sorry if this feels like i just assigned you an essay for homework; old habits die hard and all that.
I mean…LLMs are auto-sentence-finishers. They’re not trying to make points. They don’t have stances. They’re don’t “know” things in the sense that humans retain information and have some sense of what they believe is true or false (nor intention of making either a true or false statement). All they’re doing or trying to do is construct a coherent-seeming sentence – or broken down further: spit out words in an order that is plausible a human said them. When the prompt specifies WHICH human it narrows the pool of probable words.
My biggest problem with all the AI garbage, besides the dweebs who seem to think it’s some sort of messiah, is that I don’t WANT a machine to write, or draw pictures, or anything like that. I want a machine to do the goddamn DISHES and mop the goddamn FLOOR so that I can spend more time writing and drawing pictures and whatnot. They’re trying to take away the good stuff and leave us with the bullshit drudgery. It’s all bass-ackwards.
where are the 3-day work weeks, damnit?!
We want Rosie the robot! Not Skynet!
What if you could have both? Then what would be filling your days?
I always thought Jason’s automotive “would you rather” articles were some kind of burgeoning AI/LLM resistance movement that I didn’t understand.
Now I’m convinced they are, I just haven’t figured out the coded references yet.
Oh LOBSTER EMPEROR… please help me understand?
Grant me the keys to the MAGIC COMBINATION PLATTER?
Free me from these billionaires bands of rubber that hinder my minds claws from opening…
No. No. No.