Shock and awe were my reactions after my first encounter with ChatGPT, a chatbot launched by the artificial intelligence research laboratory OpenAI last November. Words sprouted onscreen as soon as I finished typing my request for a Shakespeare parody.
In a flash, ChatGPT churned out a poem addressing the Bard: "Let's see, how could we twist and bend your work, And make the old seem new, the sombre more absurd?
"Perhaps, dear Shakespeare, you'd be a rapper on the scene, Spitting rhymes and beats, with iambic pentameter lean. You'd bust a flow about young Hamlet's troubled mind, While Ophelia's love for him you'd eloquently rewind."
The amazing wordsmith was lightning-fast, writing - at my request - in the style of Shakespeare, Jane Austen, Hemingway and PG Wodehouse.
The chatbot also shared jokes albeit blandly: "Why was the math book sad? Because it had too many problems."
ChatGPT is not perfect.
When asked to write a sonnet, it wrote a poem.
When asked the differences between British and American English, it wrote: "There are also some differences in the way grammar is used in American English and British English. For example, in American English, the past tense of the verb 'to get' is 'got', while in British English, it is 'got' or 'gotten'."
On the contrary, "got" is British and both "got" and "gotten" American. ChatGPT by OpenAI, with its headquarters in San Francisco, seems to have an American orientation.
Asked which sentence is correct - "England are playing France" or "England is playing France" - the chatbot claimed the second is correct.
But "England is playing France" is American English while "England are playing France" is British English.
Corrected, the chatbot thanked me for pointing out its mistake.
To its credit, ChatGPT makes a fair assessment of its strengths and weaknesses when asked: "ChatGPT is a very powerful language model capable of generating human-like text in realtime." It agrees it is somewhat similar to the predictive text function on mobile phones.
But predictive text suggests words and phrases based on what we normally use. It is limited by the user's vocabulary.
On the other hand, ChatGPT "has been trained on a large dataset of human text... with billions of parameters". "My training dataset includes a wide range of text from a variety of sources, including books, articles and websites, from many different countries where English is spoken," it said.
"This includes text from the United States, the United Kingdom, Canada, Australia and New Zealand, as well as text from other countries where English is widely spoken, such as India, Singapore and Malaysia."
It wrote a bit of Singlish at my request but said: "However, it is important to note that ChatGPT is not a perfect writer and it may make mistakes or produce text that is not entirely coherent or appropriate. It may not always be able to generate text that is as sophisticated or nuanced as that produced by a human."
Nevertheless, its ability to write essays and code has prompted concern that it could be used for cheating.
Teachers in Singapore say they will have to set assignments that require greater critical thinking to prevent plagiarism, reported The Straits Times.
Jobs may be under threat, too.
ChatGPT claims it can be used in chatbot app for customer service, e-commerce and entertainment because it can carry on a "virtual conversation".
The economist Paul Krugman wrote in The New York Times that artificial intelligence and automation could reduce the need for some knowledge workers, such as those involved in data analysis, research and report writing.
When I put the question to ChatGPT, it said: "It is possible that language models like me may become more advanced and able to generate text more quickly and accurately than human writers in certain contexts.
"However, it is also likely that human writers will continue to have a role in creating original content and expressing personal perspectives and experiences."
While I was impressed by the speed, flow, clarity and smoothness of ChatGPT's prose, I was also struck by the absence of vivid expressions and imagery found in good writers.
It did use memorable words and images when asked to imitate great writers like Shakespeare, but when it was chatting or writing something else at my request, it used conversational language and what may be called good business English - clear and smooth but bland.
That may be because most of the content it has been trained on is written in plain language.
ChatGPT has its limitations. It hasn't accumulated knowledge beyond 2021. It can't be used for searching like Google.
But it answers your questions with instant write-ups that may be like entries in Wikipedia. Except that unlike Wikipedia and Google, it offers no links.
Yes, there is concern over the software. But when was an innovation accepted without any hand-wringing?
Even the invention of the alphabet was mourned by the Greek philosopher Plato. He was worried that the use of text would threaten traditional memory-based arts of rhetoric.
Just as humanity has evolved from hunter-gatherers to knowledge workers, technology is also evolving, assuming roles played by humans.
If man can write, so can software, with a little help from human inventors, of course.
Man and machine have become partners and might get closer still in a future resembling Kazuo Ishiguro's novel Klara And The Sun, where the robot Klara, an Artificial Friend, is close to the young girl Josie, both speaking the same language.