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 quit SYSK when iheart bought it, creating a vertical monopoly… And turning SYSK into a purely capital enterprise. Josh and Chuck rule. Wish they would do more of their own work off of the iheart platform.
Hm, I guess I haven’t paid attention to the ownership, I just skip past the ads to the content.
They will always be worth listening to.
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.
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
Not even inpainting smh
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.
Businesses should automate the executives instead of labor.
Execs won’t take the time to learn that, they will learn it only by losing market share to the competition.
“That was two golden parachutes ago, what do I care?”
By that time they’ll already be at the next company.
This is fine. Just let us know so we know what shows to avoid.
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.
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
Yea I think currently LLMs are in a stage to 2x or 1.5x the speed of a writer, but not really replace them.
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.
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.
Are we assuming AI won’t be able to create a good prompt? 😂
As usual with new technology, some jobs go away and new ones appear.
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.
No, that’s exactly how this stuff works. Lay off 80% of writers and keep all your fact checkers and editors.
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 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?
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
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”
Ah, thanks. I suppose ChatGPT’s take would be the same. - I will have to check that site out.
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.
it absolutely could not.
one of the hallmarks of how its made’s narration is the terse, accurate representation of whats going on. llms are often wrong about things and dont do great at precise descriptions to begin with.
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
I wonder how Josh and Chuck from SYSK feel about this.
What’s SYSK?
Stuff You Should Know podcast.
Stuff You Should Know! It’s a great podcast that’s affiliated with How Stuff Works, from my understanding.
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.
This seems like a really dumb idea.
Holy shit. Haven’t heard of How Stuff Works since like 2002…
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.
I wonder what they will do when the tripe the LLM spews doesn’t match the pictures they are showing.
Nothing lol.
