How Stuff Works replaced writers with GPT-generated content and laid off editors

This seems really short-sighted. Why would I go to How Stuff Works when I can just ask the LLM myself?

Maybe there's just no possible business model for them anymore with the advent of LLMs, but at least if they focused on the "actually written by humans!" angle there'd be some hook to draw people in.

The thing is, the LLM doesn't actually know anything, and lies about it.
So you go to How Stuff Works now, and you get bullshit lies instead of real information, you'll also get nonsense that looks like language at first glance, but is gibberish pretending to be an article. Because sometimes the language model changes topics midway through and doesn't correct, because it can't correct. It doesn't actually know what it's saying.
See, these language models are pre-trained, that the P in chatGPT. They just regurgitate the training data, but put together in ways that sort of look like more of the same training data.
There are some hard coded filters and responses, but other than that, nope, just a spew of garbage out from the random garbage in.
And yet, all sorts of people think this shit is ready to take over writing duties for everyone, saving money and winning court cases.
- Yeah, this is why I can't really take anyone seriously when they say it'll take over the world. It's certainly cool, but it's always going to be limited in usefulness.
  Some areas I can see it being really useful are:
  generating believable text - scams, placeholder text, and general structure
  distilling existing information - especially if it can actually cite sources, but even then I'd take it with a grain of salt
  trolling people/deep fakes
  That's about it.
- Here is an alternative Piped link(s): https://piped.video/watch?v=oqSYljRYDEM
  Piped is a privacy-respecting open-source alternative frontend to YouTube.
  I'm open-source, check me out at GitHub.
- I've graded papers from students who obviously used chatGPT to write them. They were a pass at best. Zero critical synthesis of ideas and application of them to the topic. I'm sure chatGPT has its uses but people really overhype its writing ability. There's more to writing than putting words in the right places.
- Absolutely. Creating new documentation will always be a human sport.
- I mean I would say maybe "regurgitating their training data" is putting it a bit too simple. But it's true, we're currently at the point where the AI can mimic real text. But that's it - no one tells it not to lie rn, the programmatic goal of the AI is to get indistinguishable from real text with no bearing on the truthfulness of the information whatsoever.
  Basically we train our AIs to pretend to know, not to know. And sometimes it's good at pretending, sometimes it isn't.
  The "right" way to handle what the CEOs are doing would be to let go of a chunk of the staff, then let the rest write their articles with the help of chatgpt. But most CEOs are a bit too gullible when it comes to the abilities of AI.
- Literally predictive text but for whole articles.
  It doesn't know the limits of it's knowledge or indeed know anything. It just "knows" what an answer smells like. It even "knows" what excuses are supposed to look like when you call it out.
- This is a very good write up about how ChatGPT works.
- The thing is, the LLM doesn’t actually know anything, and lies about it.
  Just like your average human journalist. If you ever read an article from not specialist journal on a topic you are familiar with - you know. This seems actually where LLM are very similar to how human brain works - if we don't know something, we come up with some bullshit.
It's a combination of three things:
1- most people still google things;
2- the more content you have the more organic traffic you're likely to attract from Google;
3- displaying ads on your website makes you money.
Websites full of LLM generated content are just the natural continuation of MFAs (Made For AdSense) and there were lots of tools on sale back then in the 2006~2008 period that promised to automatically create websites for you and fill them with randomized content that is optimized for AdSense.
This reminds me of the short story "The Great Automatic Grammatizator" by Roald Dahl. In the story a machine is invented that can write great stories, but it's creators go around buying the naming rights of authors so people will actually not their books.
- so people will actually not their books
  What?
Correct me if I'm wrong, but isn't AI generated content not copyrightable? Therefore nothing is stopping someone from taking all their content, rebranding it as "how stuff really works" or something, and then start stealing their business & ad revenue.
LLM cannot create new concepts, it can only create a mishmash of things it has been fed on.
- Humans aren’t much different. 99.9% of what we create is just a remix of existing parts/ideas. It’s why people spend 12-20 years pre-training on all the existing knowledge in the field they’re going to work in.
- Isn't that exactly how howstuffworks operates though?
- Just like Hollywood!

This is going to happen for a while. Execs who actually have no clue have now been sold on the idea that AI lets them keep making money without paying labor.

It will fail eventually when the execs eventually take the time to learn what AI is capable of and what it isn't capable of.

Who am I kidding? It'll continue indefinitely because there are few consequences for clueless executives.

Execs won’t take the time to learn that, they will learn it only by losing market share to the competition.
- By that time they'll already be at the next company.
- "That was two golden parachutes ago, what do I care?"
Businesses should automate the executives instead of labor.
What will probably happen is that people catch on that the content all reads alike and wonder why they shouldn’t just ask ChatGPT directly. Traffic to these sites die down, they panic, and start hiring writers.
I see a possibility where these sites eventually become terrible and there is a new person can come in and make content made by humans.
- Even edited by humans would be better than that

Considering most articles on the internet that don’t come from legitimate newspapers sound like they’re written by a 6-year-old who gets paid by the word, how much worse could it get?

Never ask that

People really don't understand the current state of LLM, like the pictures generated "Its a really good picture of what a dog would look like, it's not actually a dog". Like a police sketch, with a touch of "randomeness" so you don't always get the same picture.

I'm guessing they will try to solve this issue with some cheap human labour to review what is being generated. These verifers will probably not be experts on all the subjects that the llm will be spitting out, more of a "That does kind of look like a dog, APPROVED".

Let's say I'm wrong, and LLM's can make as good of an article as any human. The content would be so saturated (even a tumblr user could now make as good and as much content as one of these companies), I would expect companies to be joining in on all the strikes 😆.

Funny world we are all going into.

Boas Entradas

One thing I disagree with is the assumption that anyone could create the same article by themselves. Coming up with a good prompt is a skill in itself and not everyone is equally good at it. I actually believe a prompt writer is going to be a new profession in the near future.
- As usual with new technology, some jobs go away and new ones appear.
- Are we assuming AI won't be able to create a good prompt? 😂
I’m guessing they will try to solve this issue with some cheap human labour to review what is being generated.
They already do. These current "AI"s are starting to look more and more like Mechanical Turks, except with a couple hundred third-world wage-slaves inside the box.
Yea I think currently LLMs are in a stage to 2x or 1.5x the speed of a writer, but not really replace them.

Bizarre. Not even keep a few editors for... the editing??

I wonder how this will affect the Stuff You Should Know podcsst.

They haven’t been associated for awhile, the company owning HowStuffWorks spun off the podcasting division in 2017 before selling it to iHeartMedia in 2018 https://variety.com/2018/digital/news/iheartmedia-stuff-media-howstuffworks-podcast-acquisition-1202939938/
- Oh, great to know!! They are my favorite duo, and I often here them talk about How Stuff Works articles.
  Thank you for the link.

I've read articles that were clearly created using ChatGPT, there was no extrapolation to add context/details to illustrate their points, and parts of it read like it just pulled from a Wikipedia page. The tone felt more robotic than pieces they published 6~8 months ago.

ChatGPT can be useful when it's part of a larger writing process, but I have a feeling that sites that create prompts and paste the output as their articles will slowly die-off because the quality isn't there.

I was checking something on a Fandom "wiki" the other day and I swear to god the summary for a bunch of episodes for several shows was either written or rewritten by AI. You can tell because it uses a bunch of nonsense synonyms, like replacing the name Ray with Beam.
We're probing the limits of generative AI right now. I expect a snapback of sorts as people find what does and does not work.

Someone should create a blocklist for all these new AI-driven websites.

For me personally thee primary appeal of websites are that there's human authors behind the content... otherwise I'd just ask an 'AI' myself.

It would be great to have a list of sites so id know whose links I can just immediately ignore.

How about instead of all the tracking cookie popups for permission, we force these sites to display a message that the content is AI generated.

Why not both?

Great. Now people are going to read up a bunch of bs generated by a language model and confidently spread around "hallucinations" as facts.

They must be having proof readers
- That's optimistic.
- You know that's not how this works.
- Probably, though it might be too optimistic to assume that. However, I believe it will still result in more mistakes simply because it's harder to spot errors in an existing text than to not put errors in the text in the first place by fact-checking beforehand and then having another person proof-read.
  One of the reasons for that is that LLMs don't feel guilty when they hallucinate while most humans don't like to lie or be too lazy to fact check, and even if they don't care about that, they still have to think about getting caught and damaging their reputation, which again LLMs don't have. And you can't call stating something false as a fact in an article an honest mistake (it's negligence at best) unlike an editor's missing something (due to a looming deadline, perhaps), especially when it's assumed there won't be too many hallucinations, which isn't a certainty.

How long until we can a browser extension that lets us know when we are on a site written by AI?

I don’t mean AI detection, but instead, sites that announce they are laying off editors in favor of AI.

If there was such a thing then sites wouldn't announce they're laying off editors in favor of AI.

Creating a market for real human content? Sounds tasty

Maybe make it a co-op and put the CEO + AI article company out of business
I'm down for that

Used to be one of my favourite sites when I was younger. Haven't visited that site in ages. Holy crap, has it gone to complete shit. Like way worse than I thought possible

When I read the OP I thought "oh yeah I used to use that all the time, I wonder what its like now?". Seems to have changed a lot......
- totally unrecognizable. I can't believe I actually used to learn stuff there

I wonder how Josh and Chuck from SYSK feel about this.

What's SYSK?
- Stuff You Should Know! It's a great podcast that's affiliated with How Stuff Works, from my understanding.
- Stuff You Should Know podcast.
They got their start on HSW, but I believe the podcast division is now separate, owned by iHeart?
- Ah ok, I thought they were still some how legally related.

Holy shit. Haven't heard of How Stuff Works since like 2002...

ChatGPT comments on the news:

Prompt : In recent news, the management of "How it's Made" has fired all the writers and editors on the show and intends to replace them with a large language model. What do you think?

ChatGPT

As an AI language model, I don't have personal opinions or feelings, but I can provide an analysis based on the information available up to my last update in September 2021.

If the management of "How It's Made" decides to fire all the writers and editors on the show and replace them with a large language model like me, there are both potential benefits and drawbacks to consider:

Benefits:

        Cost Savings: Employing an AI language model could potentially reduce production costs as it eliminates the need for paying human writers and editors.
    Speed and Efficiency: AI models can generate content at a rapid pace, which may allow for more frequent episode releases or updates.
    Access to Data: AI models have access to vast amounts of data, which could result in more comprehensive and detailed explanations of the manufacturing processes.
    Consistency: AI-generated content can maintain a consistent style and tone throughout the episodes.

Drawbacks:

        Lack of Creativity: While AI models can provide factual information, they might struggle to inject creative elements or engage with the audience on a more emotional level.
    Human Touch: Human writers and editors bring their unique perspectives and storytelling abilities to the show, which might be missed with an AI-only approach.
    Reliability: AI-generated content can sometimes produce errors or inaccurate information, which would require careful human oversight and fact-checking.
    Audience Response: The audience's perception of AI-generated content might not be as positive as content created by human professionals, leading to a potential decrease in viewership.

Ultimately, the success of this decision would depend on how well the AI language model can replicate the engaging and informative aspects that made "How It's Made" popular in the first place. It's important for the management to carefully evaluate the pros and cons and ensure a seamless transition if they decide to go down this route. Additionally, audience feedback and receptiveness to the AI-generated content will play a significant role in determining the long-term viability of such a change.

That's interesting, but just so you know it's the website "how stuff works" not the tv show "how it's made"
- No shade on "how it's made", it's one of my favorite shows. But I think a LLM could probably write most of the narration. They primarily describe what is happening on screen. You might have to train one special to have information on industrial and manufacturing processes.
- Ah, thanks. I suppose ChatGPT's take would be the same. - I will have to check that site out.

This seems like a really dumb idea.

I wonder what they will do when the tripe the LLM spews doesn't match the pictures they are showing.

Nothing lol.

This is fine. Just let us know so we know what shows to avoid.

Chat-GPT became far less useful to me when I realized it will actively lie to you. It was too good to be true it turned out. These people will figure it out eventually, Chat-GPT is not an AI, it's a god damn "Chinese Room" (It's a thing in philosophy, look it up)