Academia is in a frenzy about an artificial intelligence system called ChatGPT that can write papers, reports, and responses on demand.
It stands for Generative Pre-trained Transformer and was launched on November 30 last year by OpenAI, an AI research lab.
It has both dazzled and dismayed with articulate responses and a lack of factual accuracy, which will come as no surprise considering OpenAI’s founders include the new overlord of misinformation, Elon Musk.
I asked ChatGPT to write a column about bots that write columns. That’s what it told me:
“While using bots to write might seem like a novel idea, it’s actually not a new concept. For years, news organizations have used automated systems to create basic news stories, such as: B. Stock market updates and sports scores. However, with the development of more advanced language models, bots are now able to write more complex articles and columns.
“One of the main benefits of using bots for writing is the ability to quickly generate large amounts of content. This is particularly useful for news organizations that need to produce large numbers of articles on a daily basis. In addition, bots can also be programmed to write about specific topics, which can be useful for specialized publications.
“However, there are also concerns about using bots for writing. One of the main concerns is the potential spread of misinformation. Because bots can generate content based on a set of pre-programmed rules, they may not always be able to accurately distinguish between fact and fiction. Additionally, there are concerns about job losses as more content is generated by bots.
“While it offers many benefits, such as B. the ability to generate large amounts of content quickly, it also raises important ethical and societal issues that need to be addressed.”
Of course, I then asked it to show us the disadvantages of writing columns through bots. It took 6 seconds to produce this:
“There are several disadvantages to using bots to write columns, including:
“Lack of creativity: Bots can only write based on the information they were trained on, so they may not be able to come up with new and original ideas.
“Poor understanding of context: Bots may not fully understand the nuances and intricacies of the language and may not be able to detect sarcasm or irony.
“Lack of Accountability: It can be difficult to hold a bot accountable for the content it produces, as there may not be a clear author or publisher to hold accountability.
“Lack of human touch: Bots may not be able to capture the human perspective and emotions that make columns relatable and interesting for readers.
“Lack of diversity: If a bot is trained on a specific data set, it may only be able to write in a certain style, which can limit content diversity in columns.
“Lack of Accuracy: There is a risk of misinformation if the bot’s training data isn’t accurate, since the bot can’t check or verify information like humans.”
This all sounds pretty damning, so I asked to outline the benefits of using bots to write columns. It committed but clearly wasn’t happy:
“Bots writing columns can have several advantages, such as: consistency and reliability in tone and style; Ability to generate content quickly and at scale; Reduced costs associated with hiring human authors; Potentially increased accuracy and objectivity in reporting on data-driven topics; Ability to work 24/7, which can be useful for news outlets that need to update their content frequently.
“However, it’s also important to note that bots lack the human touch and creativity that comes with human writing, and may not be able to fully grasp the nuance and complexity of certain topics.”
I couldn’t have put it better. Or maybe, according to Bot, I could have done it?
* Arthur Goldstuck is the founder of World Wide Worx and Editor-in-Chief of Gadget.co.za. Follow him on Twitter at @art2gee. This column first appeared in The Sunday Times.
