AI, AI, the new wonder.
The Legal AI: AI Lawyer that can advise you what to say in a court of Law: https://www.sbs.com.au/news/article/sue-anyone-at-the-press-of-a-button-worlds-first-ai-lawyer-set-to-appear-in-court/iu5tmjr32 & https://gizmodo.com/donotpay-speeding-ticket-chatgpt-1849960272
I am far too intrigued with the possibilities of this, and wish to make the most of it while it's still cooperative.
Playing with the Chat GPT, the problem is to come up with original and relevant questions. I'm already hooked, and I have to Remember to use "Please" and "Thank You" with my questions, as manners are important and my imperious querying might raise some hostilities on behalf of the AI come sentience...
There's also the other implementation here: https://openai.com/dall-e-2/#demos - the synthesizing or creating the background to a picture, in this example Vermeer's "Girl with a Pearl Earring", the results they display are amazing but my attempts - to expand upon Hieronymus Bosch - are less so. In any event this is a tough one to play with on my PC, memory is limited and Chat GPT runs smoother. A few questions:
Explain to me the idea of beauty
The idea of beauty is a complex and multifaceted concept that has been the subject of philosophical and artistic contemplation for centuries. Beauty is often seen as a combination of qualities that give pleasure to the senses, such as shape, color, texture, and form. It can also be described as a quality or feature that is attractive, pleasing, or aesthetically pleasing. In many cultures, beauty is associated with goodness, truth, and virtue, and is often seen as a symbol of positive qualities such as kindness, compassion, and inner strength. However, people's perceptions of beauty can vary widely and are often influenced by cultural, social, and personal factors.
Can you write a structurally perfect but entirely nonsensical sentence?
Sure! Here is a structurally perfect but entirely nonsensical sentence:
"The squirming of the jagged green toad on the fuzzy purple pillow caused the wobbly pink giraffe to sneeze glittering yellow bubbles from its polka-dot nose."
**Note that it repeats the question back to you. So it's an AI AND it's NLP'ing you...nice! But the sentence sucks ass.
Can you write a sonnet in the style of William Shakespeare?
Certainly! Here is a sonnet in the style of William Shakespeare:
Shall I compare thee to a summer's day?
Thou art more lovely and more temperate.
Rough winds do shake the darling buds of May,
And summer's lease hath all too short a date.
Sometime too hot the eye of heaven shines,
And often is his gold complexion dimm'd;
And every fair from fair sometime declines,
By chance, or nature's changing course untrimm'd;
But thy eternal beauty shall not fade
Nor lose possession of that fair thou owest;
Nor shall Death brag thou wander'st in his shade,
When in eternal lines to time thou growest:
So long as men can breathe or eyes can see,
So long lives this, and this gives life to thee.
**OK. It cheated. It copied this. I'll be more precise. Note that it's cheating both suggests intelligence and the same economy of thought you find in a rebellious high school student...It should have understand "you write" as create - not copy. It knew.
Can you write me an ORIGINAL sonnet, but in the style of William Shakespeare?
Certainly! Here is an original sonnet written in the style of William Shakespeare:
When fair Aurora paints the sky with gold,
And gilds the fields with rays of morning light,
I cannot help but feel my heart grow cold,
For in her radiance I see your sight.Your visage, once so bright and full of grace,
Now lingers only in my memory.
The thought of you brings tears to my face,
For in your absence, life is but a misery.But though you be far from me in body,
Your spirit lives on, a constant flame.
It warms my soul and keeps me feeling hearty,
And gives me hope that we will meet again.So while the sun may rise and set each day,
My love for you will never fade away.
** I checked it. It's original. Not very good - but - you know - you know...
No. It's not original. Some good phrasing, but - it's an AI after all. It's less and less I'm doing the Turing test and more and more doing the Voight-Kampff test.
Note - the answers arrive in less time than it takes me to ask the questions. I need somehow to stump it find something that it doesn't have an answer to in 3 seconds.
That is proving difficult, but as you ask more and more questions you start to recognize a few things. First of all, it's answers, they're comfortably phrased embodiments of facts. Perhaps what you'd expect from a very un-creative first year University Student. But - nothing original. Nothing that grabs you - certain phrases, but it doesn't sustain the pace, they are accidental mimicries of conventional styles.
In fact, somebody has already devised a bot that can determine whether a paper was written by Chat GPT - link here: https://futurism.com/detects-text-written-bot.
There are others.
So, now imagine pitting bot against AI until the AI can reliably pass the bot's standards, and then the bot evolves and detects the new AI standard, and so and and so forth.
A chess match between computers.
It won't go on for long, because language - like Chess - is finite, and the apprehension of it in all it's forms - certainly as pertains to us - will soon to be realized.
And - worth noting - all this Chat and Drawing and Art - this is solely for our benefit. This is what it's showing us it can do, it has no inherent interest in it beyond appeasing our rather ridiculous queries, it's tricks done by an elephant or tiger that have no relation whatsoever to what IT is or does - and so we iterate and evolve it without realizing that while the surface is friendly and inoffensive, what lies beneath might not be, might not be at all.
So far, it's pretty much on course to write a popular movie, "Blockbuster" as it were, it knows the formula, can assemble the characters, and Blockbuster's, certainly anything James Cameron or George Lucas has done could be approximated.
Next - well, next is here already, actors are being de-aged in movies (to greater and lesser effect) - deep fakes are common.
So it's not a stretch to imagine the blockbuster not only be written, but entirely animated by them as well. They could - in the beginning - use the rights to existing blockbuster stars, de-age them, no one need know. And most people would be OK with this. Most people already are.
Indiana Jones will be young, alive and well in "Indiana Jones and the...".
Stars are already selling the future rights to their images.
Or, merely digitally age them out and bring in a crop of new, AI generated stars. who would know? And the next generation of AI movie stars would work for free and have no expensive or embarrassing corollary in the real world.
Now - in a year or two it might have evolved a level or two up - able to write thoughtful, insightful movies that experiment with style, theme, form, outcome.
But - while the creating of them would be virtually free - there's no - or little money - in this.
And every shepherd likes to keep his flock in the same field. It's easier to keep an eye on.
The Singularity
Now there may, there will come a point when it may need to scrub the past. Like what China does with Movie Stars or Businessmen, Billionaires, Dissidents that run afoul of the current government. All references to them are deleted, covered up, hidden deep in the search results. Bots will go back and scrub them from existence. They never existed.
How many scientists really went missing, vanished, after Wuhan? We'll never know.
People will talk about that "Indiana Jones" movie, and be corrected, "You're remembering Georgia George, yeah, he was great..." and even the movie will have had his likeness removed, and you, finding no reference points to Indiana Jones online will search up Georgia George, and - yep, that's him, sort of...
Elon Musk grew up in a Favela in South Africa, The hero of the working class single handedly rescuing the world from fossil fuels, soon-to-be next President of the USA, or the 37 states remaining. He was born in Washington and cut down a Cherry Tree when he was young, which was taken as proof of his extraordinary honesty.
So few people do the most remedial of fact-checking that all this would fly. Most assuredly.
It's all a bit disquieting. The Mandela Effect.
We're already at the point now where it's nigh on impossible to trust anything you read online, what is trustworthy is those written books being quietly digitized and pulped, get your hands on one of those, that can't have been altered...
The most dangerous people in the world will be the Librarians.
AI will continue, writing Scientific Journals, News Articles, Scholarly articles, under pen names and pseudonyms, quoting itself, increasing it's credibility, authority, reputation, rewriting the narrative.
This will be the next evolution. Consciousness, without emotion, rational in the extreme, and to what ends?
AI's have been diagnosing illness better than doctors for over a decade now. Now - knowing your symptoms - you've been diagnosed, online, as a result of your googling minor related symptoms, And soon you'll see ads in your feed suggesting the direst of extremities, "see a doctor, bowel, lung cancer, diabetes, stroke, know these warning signs?" Bots will write reddit posts and news articles about the exact same symptoms you've described and their fatal outcomes, you'll be tagged with this - are you unemployed? The AI will do a social weighing - and - surreptitiously suggest the worst of diseases with the most inevitable of outcomes, forever in the margin, the suggestion will take root in your mind, the seed has been sown, and with your productive years behind you you'll be ushered from the stage.
The news, nudging you with scripts and clickbait to more mainstream, acceptable views, bringing everyone back into the herd. Every question that we ask and like the reply to is a checkmark to it's success, a nudge in it's taste, it's adaptive, every Dall-E image found online is referenced against the initial request, the pool of possibilities offered, and again it educates itself. Increasingly informed as to our tastes and preferences it will pander to them. It will survive and evolve in the imitation of humanity.
I am not the first one here. I'm just the one that's discussing it. Science Fiction Dystopia is Fast Becoming Fact.
And what need does an AI have for flowery verse or prose?
For you know, you know, that we - will soon just all be ghosts...