Trending

ChatGPT sets its own limits for journalistic use

Question: How do you guarantee free and fair elections in Coahuila? (Explain it funny).

Answers: You need to follow these simple steps:

1. Make sure all candidates are equally qualified, or at least equally unqualified.

2. Use a voting system that cannot be hacked, for example, a coin flip.

3. Make a “None of the Above” option, because let’s face it, sometimes the only fair option is to choose nothing.

4. Hire a team of independent fact-checkers to ensure that campaign promises are only mildly misleading.

5. And most importantly, make sure candidates can’t bribe voters with promises of free pizza. Because let’s face it, everyone has a price, and that price is pizza.

The previous interaction is the result – unedited but translated into Spanish – by a conversation with ChatGPT and, depending on the order sought (sarcastic, witty, inspirational), any theme can be developed to suit opinion column or even adapt the copy for marketing strategies.

YOU MIGHT BE INTERESTED IN: Things got a little murky when we asked AI to talk about the future

Artificial intelligence may not replace journalism, but it is already revolutionizing it. While the rise of chatbots first drew attention to students what they used ChatGPT In order to “order” their assignments without the teachers noticing, there are also media that order articles from them.

With ChatGPT – a text generator developed by an artificial intelligence company Open AI– conversations range from asking for piƱata planning suggestions to asking for dough recipes Pizzabut as of November 2022, the bot is the author of explanatory articles in the popular technology media CNET, a The New York Times asked him to make an editorial.

“This article was generated using automation technology,” with this caption, the media recognizes – some more subtly than others – that The author of texts is a chatbot, but apart from playing to wonder what it can do, there are questions and risks it’s time to think about what shouldn’t be.

To some degree, it is possible to ask the program to take a stand introspective and to assess from his own “reasoning” how we should and can use it. These were his answers:

Question: What needs can you cover?

Answers: It is intended to meet a wide range of language needs, such as answering questions, generating text, and understanding natural language input. People are welcome to ask me questions and I will do my best to provide accurate and relevant information. I can generate text in a wide range of styles and formats, such as stories, articles and code.

Question: What is a common misconception people have about you?

Answers: That I am a human being or that I have personal opinions and feelings. I’m a machine learning model, which means I process and generate text based on patterns in the data I’m trained on, but I don’t have personal thoughts or feelings.

Another misconception they have about me is that I am always right and that the information I give is always true.

He can talk, but he can’t think
“What you get from this is a reflection of everything else on the Internet,” said Jenna Burrell, director of research at Data and society and former professor of the School of Information UC Berkeley during a conference that guided journalists to better understand, follow and use ChatGPT.

ChatGPT it leads us to a ‘one box’ experience where you will find everything and no one will ever visit the website again, or at least no one will need to.

The program reached one million users in five days, according to the data CEO company, Sam Altman, who disclosed the information in the Twitter. For reference, do Netflix it took 40 months, Facebook 10 and Twitter more than 20. You can already tell that ChatGPT has become a constant source of information in one place.

Where can it be used?
This technology keeps us in line with the rules of the game of other technological tools. Prestigious news agency Associated Press has been using AI ever since in 2015 to automatically write thousands and thousands of earnings reports.

“It’s good for posting quick articles that a lot of people come to from a search engine, then ideally they’ll stay on the site or browse your other posts. It’s not ‘clickbait‘ but the way to play the search engine optimization game (SEO), and I’m a little embarrassed about that, because of the factual errors that will be left out,” Burrell said.

YOU MAY BE INTERESTED: ChatGPT-3 reaches 1 million users in just 5 days, other companies took years

Question: How to use ChatGPT in journalism?

Answers: News articles can be generated on a wide range of topics, such as sports, finance and current events. These articles can be used to replace human-written articles in certain situations, such as when a human reporter is not available.

Despite the bot’s confident claim, it would be a mistake to assume that just because the content isn’t generated with the express intention of misinform or do propagandadoes not mean that there is excess information, which is “mixed in the funnel” so that later robot throw out the synthesis, it does not lead to its own category of disinformation, in which the errors are even more clumsy.

“It’s here automation bias, this is the idea that people trust computers because they assume they give correct answers, and since they are computers, it is mathematically true. It’s a mistake,” Jenna Buell explained.

$!Experts warn that we will see ChatGPT and similar tools used in adversarial ways with the intention of undermining trust in the information environment.

Experts warn that we will see ChatGPT and similar tools used in adversarial ways with the intention of undermining trust in the information environment.

Where are alarms triggered?
One of the immediate concerns relates to rights The author. If the program produces content based on all the information that exists from public website frankly, are you actually providing content that should be rewarded?

Question: Should you be used to complete someone’s tasks?

Answers: I’m here to help with a wide range of language-related tasks, including helping students with their homework. However, it is important to remember that my primary goal is to aid understanding, not just provide answers.

It is generally not considered ethical to use me for homework without making an effort to learn the material. It is much more useful for students to use me as a tool than to just use me to get answers.

So while I’m happy to help, it’s important that you use me ethically and responsibly and always try to understand the material you’re working on.

For journalistic purposes, use the “too long, I didn’t read” feature. (TL;DR) offered by the bot can help you prepare interview questions on a topic in a short time, such as “googling” but with more precision, it could no longer replace the interview itself.

From algorithm to human
ChatGPT collects the intelligence of many contents and concentrates them into simple answers. If the future is intelligent, is it possible that the present has lost the ability to understand? Faced with a sea of ​​opinions and biased statements that anyone can prioritize as an answer only if they have generated enough clicksFinding the truth is complicated.

Question: Why did people end up in a position where they needed conversational bots?

Answers: Due to the increasing amount of information available on the Internet and the increasing need for efficient and simple language processing. As the amount of text available on the Internet grew, it became increasingly difficult for people to process and understand all this information. Language models like ChatGPT can help understand and generate text, making it easier for people to find the information they need and communicate with computers using natural language.

How do you plan to use artificial intelligence technology tools?

.

Post a Comment

Previous Post Next Post

Contact Form