We asked ChatGPT to write an article about itself. Here’s why the response is worrying
“Tell me about yourself.”
It’s a question that usually kicks off interviews with a potential employee, but this time, we asked a bot.
What followed had nothing to do with your stereotypical robot “world domination,” no sentient comments or malicious intent — but that doesn’t matter. Across the workforce and in academic settings, professionals are warily side-eyeing the latest popular artificial intelligence software, ChatGPT. Here’s why.
ChatGPT was first announced in November 2022, according to its creator OpenAI. Users can ask ChatGPT questions, tell it to write stories and more by typing in instructions for the bot.
In seconds, the program will respond with a “human-like” style based on the massive amount of text it was trained on. ChatGPT told McClatchy News that it intentionally sounded conversational to help connect with users.
“Unlike many other language models, ChatGPT is designed to respond to questions in a way that sounds natural and human-like, making it easier for people to communicate with the model,” ChatGPT said when it was asked to write an article about itself, which was 267 words long.
Next, we asked ChatGPT to explain itself to us like we were in fourth grade.
“Okay!” it answered. “Imagine you have a really smart friend who knows a lot about many things, and can answer all sorts of questions you have. That’s kind of like what ChatGPT is! It’s a computer program that’s taught a lot of information about many topics, so it can have conversations with people and answer questions. Just like your smart friend, it doesn’t always get things right, but it does its best to help you!”
The program’s adaptability to requests and human-like responses is leaving some, from technology experts to teachers, on edge with worries about what could be automated in the future.
‘Will you replace people’s jobs?’
Workers are already considering what software like ChatGPT means for the future of their job industry, according to a study from SortList which polled 500 ChatGPT users in six different countries.
About 23% of employees working in the software and tech fields are concerned about losing their job due to ChatGPT, according to the study. More than 40% of employers showed interest in ”hiring” ChatGPT as a marketing copywriter, the study said.
According to ChatGPT, it is “designed to assist and augment human tasks, not replace them.” However, Columbia Business School professor Oded Netzer told CBS MoneyWatch that while it is more of a supplemental tool for jobs, it could do more than that for simple tasks like basic programming.
“If you are writing a code where really all you do is convert an idea to a code, the machine can do that. To the extent we would need fewer programmers, it could take away jobs. But it would also help those who program to find mistakes in codes and write code more efficiently,” Netzer told CBS MoneyWatch.
Other professional fields could see a change in workflow due to artificial intelligence like ChatGPT, including mid-level writing, advertisement, media planning and legal documentation, CBS MoneyWatch reported.
“ChatGPT and other AI technologies have the potential to change the nature of work, but they will not replace the need for human workers,” ChatGPT told McClatchy News when asked about it potentially replacing jobs. “Instead, they will complement and enhance human capabilities, leading to more efficient and effective outcomes.”
‘Can you help me pass a test?’
ChatGPT kindly asked us not to use it to cheat on a test, but some students have taken advantage of AI in school.
School districts across the country are grappling with the new territory as younger generations get to know programs like ChatGPT. Some have resorted to banning the program entirely.
“Like many other technologies, it may be that one district decides that it’s inappropriate for use in their classrooms,” OpenAI policy researcher Lama Ahmad told Fortune. “We don’t really push them one way or another. We just want to give them the information that they need to be able to make the right decisions for them.”
School districts in Seattle, Los Angeles and New York have already opted to ban ChatGPT to crack down on possible cheating and plagiarism, Forbes reported.
One user on Twitter took a mock SAT exam with the help of ChatGPT and scored 1020 out of 1600 — which is just a little worse than average, according to College Simply.
“It’s important to remember that the purpose of a test is to evaluate your understanding and mastery of the material,” ChatGPT told McClatchy News. ”Cheating, or relying solely on external sources like myself, undermines the value of the test and does not promote learning or growth.”
I made ChatGPT take a full SAT test. Here's how it did: pic.twitter.com/734sPFU3HY
— teddy (@teddynpc) December 2, 2022
In the midst of AI knocking on education’s door, Stanford University’s Victor Lee, an associate professor of education and the faculty lead for the accelerator initiative on generative AI in education, said it was an opportunity to take advantage of the technology.
“We have a glimpse of new things that are going to be built with generative AI,” Lee said in a statement. “As a first step, we need to seriously examine how generative AI is changing how different fields and disciplines do their work and what ideas students need to develop to both build and use AI for humans rather than in place of humans.”
To combat ethical issues such as cheating or plagiarism in academic settings, OpenAI says it is actively working on a Classifier, which would help professionals identify if text was written by an AI like ChatGPT or a human.
“We are engaging with educators in the U.S. to learn what they are seeing in their classrooms and to discuss ChatGPT’s capabilities and limitations, and we will continue to broaden our outreach as we learn,” OpenAI said in a release. “These are important conversations to have as part of our mission is to deploy large language models safely, in direct contact with affected communities.”
Child-free neighborhoods? TikToker’s plea divides adults. ‘As a mom, I agree’
Titanic conspiracy theory has millions of minds blown on TikTok. ‘You got me thinking’
Eating one wild fish is the same as drinking contaminated water for a month, study says
‘Worst-case scenario’ dodged by 19 feet in near collision of big space debris, lab says