8
I wonder how Josh and Chuck from SYSK feel about this.
this post was submitted on 26 Jul 2023
8 points (100.0% liked)
Technology
34395 readers
453 users here now
This is the official technology community of Lemmy.ml for all news related to creation and use of technology, and to facilitate civil, meaningful discussion around it.
Ask in DM before posting product reviews or ads. All such posts otherwise are subject to removal.
Rules:
1: All Lemmy rules apply
2: Do not post low effort posts
3: NEVER post naziped*gore stuff
4: Always post article URLs or their archived version URLs as sources, NOT screenshots. Help the blind users.
5: personal rants of Big Tech CEOs like Elon Musk are unwelcome (does not include posts about their companies affecting wide range of people)
6: no advertisement posts unless verified as legitimate and non-exploitative/non-consumerist
7: crypto related posts, unless essential, are disallowed
founded 5 years ago
MODERATORS
What's SYSK?
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?
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
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.
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.
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.
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.
Even medium human writers can comprehend their work as a whole, though. There is a cohesiveness even to the bullshit. The LLM is just putting words down that match the prompt. It's rng driven, readable Lorum Ipsum.
If the results were still edited afterwards, there may be some merit to the output, but any company going full LLM isn't looking for quality. They want to use it to churn out endless content that they simply can't get from even a team of humans. More than could be edited even if they kept editors on staff.
Even medium human writers can comprehend their work as a whole, though
Sure, but a lot of humans are rather bad writers.
but any company going full LLM isn’t looking for quality.
That is true for 24h news cycle of online media, regardless LLM.
Sure, but a lot of humans are rather bad writers.
Bad writing is still a step above rng junk, imo.
but any company going full LLM isn’t looking for quality.
That is true for 24h news cycle of online media, regardless LLM.
Yes, that was my point. Setting up your company to put out more content than can possibly be processed by humans is a glaring sign of their values - ie quantity far above quality.
Bad writing is still a step above rng junk, imo.
I'v read writing worse than GTP. I had to help someone write an essay - and I just wrote it for him in the end, because he absolutely lacked the skills to write a long meaningful text. At at the same time - genius of a percussionist.
Do you think that person was signing up for jobs writing for blogs or content farms?
Have you read some low quality journalism? The whole yellow press can be replaced with GTP and no one would ever see a difference.
Ok, so do you wanna talk about your terrible writing partner in school? Or "yellow press"? Or maybe the topic of the article, which isn't journalism in the slightest? Or how about my point, which was, again, that even bad writers have context, as opposed to an LLM which is just filling in the arbitrary patterns it's programmed to delineate. Readability is not what I'm talking about.
That's how you get the room
Did you get the room you were looking for, since you asked for it thrice? Trivago.
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.
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.
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.