Features

A dip into Artificial Intelligence (AI)

Published

on

“In Lanka’s bosom where the trade winds sigh/ A story unfolds, in nature’s embrace,

Amid the palms, ‘neath the cerulean sky, / A vivid tapestry of time and space.

Jasmine whispers perfume the warm air./ Ceylon’s canvas painted gold and green,

Echoes of history linger and share/ In ancient ruins, a past unseen.

Beside the tranquil waters of the lake/ Lotus blooms in serene contemplation,

A tranquil dream in natures sweet remake,/ A land adorned with tales of elation.

Oh, Sri Lanka, in beauty’s own trance/ Dancing freely in nature’s rhythmic dance.”

This poem can be taken to be John Keats on Sri Lanka. It is not. It was generated in a few seconds by Artificial Intelligence!

Personal

I did not want to get to know about Artificial Intelligence (AI) because all this technology and very rapid developments bother me, nay frighten me. I shuddered when Dolly was cloned; cannot understand how people use robots in their homes programmed to do household chores; and positively froze with apprehension reading Kazuo Ishiguro’s fifth novel Never Let Me Go (2005) about humans being cloned for donation of organs for transplanting to ‘real’ ill humans.

I am certainly old fashioned and maybe backward too. But that is a trait of the older person and more so of a woman. To my way of thinking, robots are OK in factories taking over repetitive tasks which humans did since Henry Ford developed the assembly line technique of mass production in his Ford car manufacturing company. But too much technological advancement is dangerous as is AI. Amazon’s Alexa answering my questions, playing requested music, even telling me a funny tale, was OK, but further developments in this sphere may lead human beings to trouble. Or at least that is my very uninformed opinion.

I had my first taste of Artificial Intelligence very recently and was completely floored and lost in wonder; but praise withheld since I have read of dangers of AI.

Let’s start with a definition because many who read me may be akin to me, not knowing much about this new phenomenon. It is “the ability of a digital computer or computer controlled robot to perform tasks commonly associated with intelligent beings. The term is frequently applied to the project of developing systems endowed with the intellectual processes characteristic of humans such as the ability to reason, discover meaning, generalize or learn from past experience.

Since the development of the digital computer in the 1940s, it has been demonstrated that computers can be programmed to carry out very complex tasks – such as discovering proofs for mathematical theorems or playing chess – with great proficiency. Still, despite continuing advances in computer processing speed and memory capacity, there are as yet no programs that can match full human flexibility over wider domains or in tasks requiring much everyday knowledge.

On the other hand, some programs have attained the performance levels of human experts and professionals in performing certain specific tasks, so that artificial intelligence in this limited sense is found in applications as diverse as medical diagnosis, computer search engines, voice or handwriting recognition and chatbots. And what about cars that are driverless but driven by AI and already on the roads in the US.

One-shot experience

My son logged into ChatGPT with me beside him: skeptical and with a no-use-to-me attitude. Soon enough I was awe struck and completely fascinated; amazed and admiring too. Our first request was to compose a sonnet on Sri Lanka in Shakespeare’s style. Before I could release ten tentative breaths, the words and lines began to appear rapidly on screen:

“Upon the shores where Indian breezes dance/ A jewel set in azure Indian seas

Fair Sri Lanka, in nature’s sweetest trance./ Her beauty whispers on the tropic breeze.

Amidst the palms, where emerald fields unfold,/ Tea plantations cloak the hills in green,

And tales of ancient kingdoms, long been told,/ Beside in ruins, by time’s touch unseen.

In Kandy’s realm, where sacred temples rise,/ The echoes of devotion softly ring.

As elephants, adorned in grandest guise/ Bear history in their stately, graceful swing.

Oh Lanka! Thine allure is as the moon. /A timeless ode in nature’s sweetest tune.”

This definitely is a sonnet since it has 14 lines. And Shakespeare made the last couplet the crux of the sonnet, a most significant summary. This is what the last two lines of the AI sonnet are: “Oh, Lanka!……. sweetest tune”

I faulted AI that the poem in Keat’s style was so similar to the Shakespearean sonnet, having 14 lines to boot. “Looks as if AI got it a bit mixed up!” Son said it remembered the conversation thread since we first asked for Shakespeare, and kept within the sonnet theme, rather than starting from zero, similar to how a human conversation would unfold.

The next request was for a paragraph on Ranil Wickremesinghe written in Jane Austen’s style. And there in almost the blink of an eye appeared rapid writing on our Prez with long convoluted sentences and Austenisque use of the English language.

We asked for a paragraph on happiness. Here is what we got, rapid fire appearance on screen. “Happiness is like catching a glimpse of a rainbow after the rain – a fleeting and beautiful moment that leaves you feeling warm and content. It’s the gentle hum of laughter in the air, the comfort of a familiar embrace, or the simple joy found in the small, everyday wonders. It’s not a constant state but a collection of moments, both big and small, that weave together into the tapestry of a fulfilling and meaningful life. It’s a journey, not a destination, and often resides in the appreciation of the present and the connections we share with others.”

Comments? Complaints? To me a mite sugary with language slightly overdone; but truths and keeping to the subject are very evident.

To define ChatGPT is this Wikipedia reference: “ChatGPT, which stands forChat Generative Pre-trained Transformer, is a large language model-based chatbot developed by OpenAI and launched on November 30, 2022, which enables users to refine and steer a conversation towards a desired length, format, style, level of detail and language.” Its developer is OpenAI, a non-profit which has now partnered with Microsoft Corporation.

Fears

The computer’s wizardry, as demonstrated, left me a long ago teacher with the fear that kids could get AI to do their homework. Unless the teacher was sharp and on the lookout for fraudulent pranks, s/he could easily give the child an A+, the homework not cribbed nor shoddily done but clever and comprehensive. This applies to language and literature questions. It sure must apply to other subjects as well. Getting a chatbot to do your homework is not copying nor plagiarism; but it definitely is cheating.

That is one minor danger. Many more serious are being pointed out.

I read this article titled “AI poses ‘Risk of Extinction’ Industry Leaders Warn” in the New York Times which sent shivers down my spine. Its subtitle was “Future systems can be as deadly as pandemics and nuclear weapons.” Quoted are excerpts from it:

“Eventually, some believe, AI could become powerful enough that it could create societal-scale disruptions within a few years if nothing is done to slow it down, though researchers sometimes stop short of explaining how that would happen…This month, Mr Altman, Mr Hassabis and Mr Amodei meet with President Biden and VP Kamala Harris to talk about AI regulation… and warned that the risks were serious enough to warrant government intervention and called for regulation of AI for its potential harms.”

In contrast are the advocates of AI. Marc Andreessen had a very long article giving the positives of AI, again in the NYT. I quote from two paragraphs:

“What AI offers us is the opportunity to profoundly augment human intelligence to make all of these outcomes of intelligence – and many others, from the creation of new medicines to ways to solve climate change to technologies to reach the stars – much, much better from here.

AI augmentation of human intelligence has already started …. and will accelerate very quickly from here – if we let it.”

Interesting fact

I read that the earliest substantial work in the field of AI was by Alan Mathison Turing. In 1935 he described “an abstract computing machine consisting of a limitless memory and a scanner that moves back and forth through the memory, symbol by symbol, reading what it finds and writing further symbols.”…….. “All modern computers are in essence universal Turing machines.”

Turing was the cryptoanalyst who with others was closeted at Bletchley Park, Buckinghamshire, the principal centre for Allied code-breaking during WW II, and set the tasks of decrypting German intelligence messages, which they succeeded in doing.

Click to comment

Trending

Exit mobile version