Home » It’s Time To Talk About Artificial Intelligence (AI) In The Automotive Media Space

It’s Time To Talk About Artificial Intelligence (AI) In The Automotive Media Space

Ai Top 1
ADVERTISEMENT

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“.

Vidframe Min Top
Vidframe Min Bottom

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!

ADVERTISEMENT

“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.

ADVERTISEMENT

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.

ADVERTISEMENT

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.

Photo Credit: Hearst

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.

ADVERTISEMENT

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:

Photo: Metro Moulded Parts

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?

Photo: YWAS

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:

ADVERTISEMENT
Photo: M&P Instagram

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.

ADVERTISEMENT

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.

ADVERTISEMENT

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.

ADVERTISEMENT

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.

 

ADVERTISEMENT
Share on facebook
Facebook
Share on whatsapp
WhatsApp
Share on twitter
Twitter
Share on linkedin
LinkedIn
Share on reddit
Reddit
Subscribe
Notify of
161 Comments
Inline Feedbacks
View all comments
GirchyGirchy
GirchyGirchy
12 hours ago

Mmmmmmm, bake pads.

FormerTXJeepGuy
FormerTXJeepGuy
14 hours ago

I absolutely loathe AI and think that the whole “in the voice of” stuff shouldn’t be legal unless you, as that voice, has opted in to allow it to do so. Its theft and plagiarism using fancy technology

DONALD FOLEY
DONALD FOLEY
1 day ago

A.I. could be a matter of life and death journalism such as The Autopian, but it’s use in public policy could even be a literal matter of life or death. It’s alarming that HHS used it to contribute to the Make America Healthy Again report. RFK Jr.’s “Healthy” Report Cites Fake Studies, Gets Busted | National Review

Ben
Ben
1 day ago

huge legions of people catfished into following robots on blogs/twitter/maybe even insta/YouTube

Already happening on YouTube. There are AI-generated channels spitting out mounds of inaccurate trash that are getting massive clicks. Certainly enough to justify the relatively small investment it took to “create” them.

The problem is this stuff is poisoning the well. Let’s say AI does kill off all more traditional media sources. That would be it. There would never be another David Tracy or Jason Torchinsky to mimic. All you’d get in this AIpocalypse is regurgitated content that could never feel new and would be full of factual inaccuracies.

I don’t think AI can realistically replace true creatives. My biggest fear is that C-levels who make the final decisions about this stuff won’t figure that out until they’ve laid off all their creatives and the media landscape is a barren wasteland.

Dan1101
Dan1101
1 day ago

There are a bunch of new writers on a site that sorta rhymes with Robtnik, and I’m fairly sure they are AI.

Stryker_T
Stryker_T
1 day ago
Reply to  Dan1101

probably the last time I really visited that site the way I really used to was one day they posted 2 almost identical posts about the same subject right on top of each other, but one had a different lede image and a slightly different title, slightly different content, supposedly written by the same person.

Last edited 1 day ago by Stryker_T
Reasonable Pushrod
Reasonable Pushrod
1 day ago
Reply to  Dan1101

I’m 99% sure those word vomits have been AI created.

TurtleRacer427
TurtleRacer427
1 day ago

This site has always felt like I’m sitting on my porch with you guys talking cars. That’s why I’m on here everyday 🙂

Ryan L
Ryan L
1 day ago

Everything is going subscription and walled garden… can’t say I blame any content creator or knowledge provider for wanting to keep AI from stealing from them.

I do think the added benefit is that eventually folks will get tired of the brain cycles utilized trying to figure out if its a person or computer and will end up seeking out direct one to one interactions.

Yall seem to have a pretty good handle on it and so far it seems like the Money Men have their heart in the right place. Hold fast young men. HOLD FAST.

Ben Eldeson
Ben Eldeson
1 day ago

I am about to turn 48 years old. And I have about 25 years of experience working as a graphic designer, animator, creative director, occasional video editor, voiceover person. I’ve also worked on photo shoots, designed trade show booths, T-shirts and apparel, and UI and web designer.

Everything and more that I just mentioned are things that various AI tools can now do easily. Even old standbys and industry standard tools like all of the Adobe apps ( Photoshop, Illustrator, etc ) are now AI-enhanced. Many features that save me an unbelievable amount of time.

This is going to eat everyone’s lunch if you are in the creative field. All of the people I went to college with work in the entertainment industry. They are all scared. A lot of their friends and former coworkers are not getting new gigs.

At this point I am now planning for how to wrap up my career. My wife and I both work as creatives and luckily have lived cheap ( still driving a 30 year old Tacoma ) and have saved and invested. But the reason is that I see whats going to happen. What I have done my entire career is about to get upended. The same way that computers upended the industry when it all went from optical and print based technology to digital. Some made the leap, others didn’t. I’m not super interested in having AI become more and more of a thing I have to deal with. I already deal with it enough and hate it. For those whom are young? Good luck.

Mike
Mike
1 day ago

I’m already a member, but can we all just start a “make Adrian miserable” fund? Anytime he’s cranky, it’s gold. I don’t have good ideas on how to make him miserable, but I’ll contribute to the cause.

Jerry Johnson
Jerry Johnson
1 day ago

I want to admit, guiltily, that I once was curious and asked ChatGPT to write an article in the style of David Tracy about a road trip in a failing Dodge Neon with several breakdowns. It just didn’t have the same “pizazz” that David has, and it lacked a lot of technical information but it had some funny quips and phrases thrown in.

If someone knew nothing about cars, they might have bought it, and honestly that kind of scares me.

Kidneystone
Kidneystone
1 day ago

I wonder if AI pulled the “engine that refuses to die” line from this article: https://www.quadratec.com/c/blog/history-cherokee-xj-part-three-refusal-die

Vee
Vee
1 day ago

Regarding the infamous Purple Cars of machine generated imagery output, they’ve become so pervasive that I’ve even seen people put them in Youtube thumbnails without knowing they aren’t real.

One thing you must always remember is that this is just twin turbo nitromethane fueled version of autocorrect. It’s just guessing based on what’s weighted to be most likely. It’s passable if you don’t have actual reading comprehension, but for those who do it’s like a teacher grading language arts homework from nine year olds in that every third word is a functional fascimile yet still a mistake.

Albino Kangaroo
Albino Kangaroo
2 days ago

While The Autopian normally does a good job of interviewing experts to lend an article credence I feel they missed the mark on this one. While (human) authors are experts on journalism and auto’s I don’t think they should have used a basic ChatGPT model to make bold statements about the impact of AI on journalism. ChatGPT is a bit of a parlor trick designed to showcase the platform and draw people to possible commercial uses using the underlying LLM technology. By design it will make things up. You ask it a question and it has to provide a response. I don’t know enough about the space but I am guessing there are journalism specific AI models that are trained to output articles much closer to acceptability than the small case study in this article. Those models are trained to more specific sources and usually given ground truth examples that help to reduce the wild west of responses that come out of a general generative tool. 

Ben
Ben
1 day ago

 ChatGPT is a bit of a parlor trick

That’s the dirty little secret of AI though: It’s all smoke and mirrors. None of it is “intelligent”, it’s a system to make you think it’s intelligent. There’s no training data set that can change that.

To further the magic analogy, no matter how well a magician can do a levitation trick, they will never actually be able to fly.

That isn’t to say there are no uses for the technology. Creating new content out of whole cloth is likely to be problematic until there is a fundamental shift in how it works though.

It'll buff out
It'll buff out
2 days ago

So we have learned that AI, can do a decent “impersonation” of Torch and Tracy, but I have little faith…..

Microsoft co-pilot has no idea what the correct spark plugs are for 1990 Mustang GT, and with the amount of data that is out there, it still could not get that one right? I ordered those Motocraft suckers, because I was too lazy to cross reference them on Rockauto.com, and to cheap to pay the shipping. When I compared them to the ones I removed, I am pretty sure that the piston would have smashed right into them on the compression stroke, they would stick so far dwon into the head.

So after reading this article, I decided to ask for some more sage advice, on a more personal level, and got this nonsense answer…..

“Jason Torchinsky, a well-known automotive writer, has written extensively about taillights, but I couldn’t find a specific recommendation from him on the best tail light bar.”

I don’t konw if AI is stupid, or like my wife says “just doesn’t listen”.

I’ll take my chances and continue to get my information and entertainment from actual people, Thanks.

But I do like that obviously BMW inspred “brake contraption thingy” it drew….Might make a poster of that for the garage wall.

Last edited 2 days ago by It'll buff out
Captain Muppet
Captain Muppet
2 days ago

I once had an argument on the internet, in which I was right and the idiot who was wrong kept quoting the same non-fact from multiple sources that all ended up actually quoting the same source: an early internet page written by one guy who was wrong. And an idiot. But he did at least have opinions and a website.

At some point the mass of previous data that AI mines for facts will become mostly AI generated, at which point it’ll become even less reliable a source of information than it is now.

This is only going to get worse.

Yay.

Lewin Day
Editor
Lewin Day
2 days ago
Reply to  Captain Muppet

I had an experience like that. An otherwise very knowledgeable engineer was making brazen claims about the prevalence of sand casting over die casting. I traced his source (which he refused to share) and it was one random line in a paperback book from 2001, and not backed up at all.

So much worse now there are legions of people that put 100% faith in whatever random alphabet soup an AI coughs up…

Vanillasludge
Vanillasludge
2 days ago
Reply to  Lewin Day

At least AI is really fucking confident when it’s wrong. None of that “possibly” bs.

I have never had chatgpt answer a question with “You know, I’m only guessing, but…..”.

Vanillasludge
Vanillasludge
2 days ago
Reply to  Captain Muppet

You’ve just encapsulated the entire user experience of the internet since 1992 in one posting.

Captain Muppet
Captain Muppet
1 day ago
Reply to  Vanillasludge

In 1992 I used to use the internet to find a satellite image of the windowless computer lab I was in to find out if the rain had stopped.
It seemed like a miracle.

It’s been a long spiral down from there.

Ben Eldeson
Ben Eldeson
1 day ago
Reply to  Captain Muppet

I remember my first “Email” circa 1994 or something. It was a blue field with some text.

Mouse
Mouse
3 days ago

Both samples definitely sound like someone doing a Tracey/Torch impression. Not terrible impressions. Impressions enough to be recognizable as impressions of who they purported to be, but very very very clearly not the real thing.

Harvey Pärt
Harvey Pärt
3 days ago

I did like the goat and sewing machine bit.

Lewin Day
Editor
Lewin Day
2 days ago
Reply to  Harvey Pärt

The Goat and Sewing Machine would be an excellent name for a pub, with a few top notch lagers and a middling if passable lamb curry on the menu.

Harvey Pärt
Harvey Pärt
1 day ago
Reply to  Lewin Day

Damn you, now I want a cold lager.

Tim Cougar
Tim Cougar
3 days ago

At some point the amount of old computers in Jason’s basement will reach critical mass and achieve spontaneous sentience. No doubt it will imprint on Jason, he being the only humanoid it knows.

That is the only AI entity whose output I would be interested in reading.

Joe D
Joe D
2 days ago
Reply to  Tim Cougar

A hardwired Sinclair superentity, here to impose Changli reverence and amber turn signal obedience

Shooting Brake
Shooting Brake
3 days ago

Yall are doing great work! Keep it up!

Anoos
Anoos
3 days ago

If someone replaced 87.2% of automotive youtube content with AI generated garbage, it wouldn’t lower the overall quantity.

I’m sure AI can recite a manufacturer press release as well as most others. If a formula can make your video, it’s your own fault for being formulaic.

Also, it seems like a good portion of automotive youtube is already AI generated garbage of slide shows and unrelated video clips under a computer-generated voice.

I am curious to see what AI thinks is a quirk and / or feature.

Last edited 3 days ago by Anoos
Jonathan Green
Jonathan Green
1 day ago
Reply to  Anoos

Too true. AI, or “generative AI”, as my son has told me, lacks “judgment” and “morality”. Those are the only words I can think of for it right now, but think about it: AI is basically making shit up, but without limitations as to knowing when to stop making shit up, or what ingredients to include in its calculations when making shit up…

Tom Trutna
Tom Trutna
3 days ago

I’ve been wasting hours of my life since October 1966 when I received my first copy of Car and Driver. My interest in cars has always been tempered by the quality of the writing. AI can’t touch this: https://www.caranddriver.com/features/columns/a15125632/david-e-davis-jr-drivers-seat-may-1967/

Tbird
Tbird
2 days ago
Reply to  Tom Trutna

So much this, C/D subscriber since 1991. The journey was as, if not more important than the car. I get the same vibe here from Mercedes in particular. Take me on a voyage.

Xt6wagon
Xt6wagon
3 days ago

Wait there was a trash-99? My sister had a trash-80 w 2 5.25 floppies and a external cassette player. Couple random programs on cassette.

Jason Torchinsky
Admin
Jason Torchinsky
2 days ago
Reply to  Xt6wagon

That’s a Texas Instruments TI 99/4A!

John Fischer
John Fischer
1 day ago

My first computer, and I still have it in a box along with dozens of cartridges for it.

Highland Green Miata
Highland Green Miata
14 hours ago

My first computer also. Loved it.

1SG
1SG
3 days ago

This was a good article and so I finally joined in order to support the continuation of human auto writers. Also, so I can one day explain my Datsun/Nissan theory explaining how they go from epic to mediocre and back.

Utherjorge, who has grown cautiously optimistic
Utherjorge, who has grown cautiously optimistic
3 days ago

I use AI-checkers all the time. First, I’d like to know what was used to generate the AI pieces in question.

DT’s came up as clean with checkers, though there were enough hits that I would investigate further.

Torch’s came up as a 100% AI-written article on a “good” checker.

Dumb Shadetree
Dumb Shadetree
1 day ago

As a human, I would have known DT’s was sus. It isn’t nearly worshipful enough towards XJ’s to be real. Torch’s though, that might have fooled me.

It’s funny how my instincts don’t match those of the AI checkers.

Utherjorge, who has grown cautiously optimistic
Utherjorge, who has grown cautiously optimistic
1 day ago
Reply to  Dumb Shadetree

Good detection is a combination of touch and tech

Mr E
Mr E
3 days ago

The AI Jason blurb was slightly more believable, but we’re all fortunate there’s a real person behind those wacky words, in the same way I am a fan of Rush in part due to Neil Peart’s lyrics.

I will admit to using AI to generate an album cover for my band (my artistic talents lie in music, not visual art), but that’s the extent of it. Interestingly, the resulting image was almost exactly as I envisioned it in my head, although it took a lot of redoing of prompts to get it right. It still looks kinda fake, though, so I’m going to have my art school daughter paint her own version of it to give it some humanity.

Any publication that uses AI for content is cheap and lazy and doing themselves and their readers a disservice.

And don’t get me started on AI-generated music.

Vee
Vee
1 day ago
Reply to  Mr E

With my music I’ve been debating on intentionally leaving in some roughness just so I don’t get hit with accusations. Stuff like not quantizing something I record into the piano roll or not cutting out string slide sounds on the guitar. It’s pretty bad when you have to eschew professionalism to avoid baseless claims. Although machines won’t make those simple human errors it still brings the ceiling down on quality.

Mr E
Mr E
1 day ago
Reply to  Vee

That is exactly what I do. I approach music the way it was made in the 70s, where they focused more on feel than total accuracy. The only thing that is quantized is the click track – a necessity since the gent I’m making music with is across the Atlantic in Wales. I’ve learned that perfection does not exist in anything, so I’ve stopped chasing it.

Modern music – actually most modern everything – has lost the element of surprise. That weird noise and laugh at the beginning of “Roxanne” by the Police happened because Sting sat on a piano before a vocal take, thinking the keyboard cover was down. It wasn’t, it made a bizarre chord, he laughed, and they left it in the song for the hell of it.

161
0
Would love your thoughts, please comment.x
()
x