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)
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.
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.
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:
<pre style="background-color:#ffffff;">
<span style="color:#323232;">Cost Savings: Employing an AI language model could potentially reduce production costs as it eliminates the need for paying human writers and editors.
</span><span style="color:#323232;">Speed and Efficiency: AI models can generate content at a rapid pace, which may allow for more frequent episode releases or updates.
</span><span style="color:#323232;">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.
</span><span style="color:#323232;">Consistency: AI-generated content can maintain a consistent style and tone throughout the episodes.
</span>
Drawbacks:
<pre style="background-color:#ffffff;">
<span style="color:#323232;">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.
</span><span style="color:#323232;">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.
</span><span style="color:#323232;">Reliability: AI-generated content can sometimes produce errors or inaccurate information, which would require careful human oversight and fact-checking.
</span><span style="color:#323232;">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.
</span>
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.
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.
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.
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 😆.
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.
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.
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.
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?
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