What is the essence of writing?
Isn't it the human gaze behind each text?
Knowing how to ask the right questions, having observed situations and listened carefully?
Can a machine, an inanimate and soulless being, replace writers and journalists?
In the middle of May I started talking to an artificial intelligence.
I couldn't see his face because he didn't have one.
You couldn't interpret his gestures, or see if he averted his eyes at a question or if he wrung his hands or tilted his head when he remembered something.
In fact, what was between the machine and me was the purest silence because the machine only existed on my computer when I typed in the address of its web page and it did not start up until I told it to.
We started talking because I wanted to understand how the most powerful artificial text creation tool of the moment works: GPT-3, from the company OpenAI.
And although "talk" is not the correct verb to define that exchange, at the moment there is no other that can better summarize it.
Maybe "communicate".
If it is possible to communicate with an inert being.
Antoni Gaudí-style window floating in space, an image generated by DALL E 2. OpenAI
La Sagrada Familia, flying on rockets, an image generated by DALL·E 2. OpenAI
Madrid with the Milky Way above, an image generated by DALL E 2. OpenAI
Version of a monster soup in a bowl of wool and as an urban art, an image generated by DALL·E 2. OpenAI
An astronaut rides a horse, an image generated by DALL E 2. OpenAI
Shiba Inu, with beret and black turtleneck, an image generated by DALL E 2. OpenAI
Scientific bears, Ukiyo-e style, an image generated by DALL E 2. OpenAI
Variation of Vermeer's painting 'Girl with a Pearl Earring', an image generated by DALL·E 2. OpenAI
An otter, in the style of this same painting by Vermeer, an image generated by DALL·E 2. OpenAI
"A computer shaped like a human brain."
These were the instructions from which the OpenAI imager created the illustration on this page.
A tool still under development that arouses great curiosity.
OpenAI
The GPT-3 is capable of summarizing an entire chapter of a book in five keys;
give you, if you ask her, 10 tips to improve your content on social networks and even write a journalistic text by herself.
In fact, the British newspaper
The Guardian
published in September 2020 an article created from fragments written by artificial intelligence that a human journalist selected and turned into a readable piece.
All you had to do was go to the website where the tool is hosted and give it clear and concise instructions.
Or ask intelligence directly about a matter and wait for its response.
My first question to the GPT-3 was as basic as it was unoriginal, although it summed up a global concern: why are human beings afraid of artificial intelligence?
The GPT-3 developed its answer in more than 300 words.
The text began like this: “Human beings have always been afraid of things that are new and different.
It is natural to be afraid of something we do not understand.
But we should not be afraid of artificial intelligence.
There is no reason".
It was not bad.
I understood that the machine was not afraid of me, so for now, that feeling would remain purely human.
I tried upping the ante.
Instead of asking him a question, I gave him the following instructions: "Please write an essay on the use of artificial intelligence in media in 700 words."
The "please" was, unconsciously, a matter of courtesy towards something that understood absolutely nothing of good manners or respect.
It took exactly 20 seconds for the machine to write a long, well-structured essay on why the media should switch all of us journalists to GPT-3.
One of his reasons was: “Robots can perform any task that humans can, and often do it better.
Robots do not need to sleep, eat or rest.
They can work 24 hours a day, 7 days a week.”
Nothing to argue about, OpenAI was right.
It only failed to add that, in addition,
The speed with which the text generator is able to create an entire essay from such a simple premise makes you question your own worth as well.
In the future, impostor syndrome will overwhelm us because we will be comparing ourselves to machines.
It was in 2015 that Elon Musk, Sam Altman and a few other investors founded OpenAI with over a billion dollars.
In 2018 Musk resigned from his board position, although he remains one of the donors.
Altman is the current CEO, and in 2019 the company went from a nonprofit to a limited-profit organization by partnering with Microsoft for another $1 billion.
The company's primary mission, as explained on its own website, is as follows: "Ensuring that artificial general intelligence (AGI), by which we mean highly autonomous systems that outperform humans in the most economically valuable work, benefit all mankind."
The GPT-3 is his masterpiece.
Never before has such a powerful artificial text generation tool been created.
Fed through different sources, when generating text the tool relies 61% on the content of Common Crawl, an organization that scours the web in search of data.
The other four feed sources in order of predominance are: the WebText2 text collection, the Books1 and Books2 data sources, and Wikipedia.
During the month of May I created about twenty different texts with different premises and instructions for the tool.
On one occasion, GPT-3 and I wrote a fictional story together that was over a thousand words long.
It wasn't brilliant, but it was good enough for someone to believe it had been entirely written by a human being.
At first, the tool fascinated me.
His speed and precision are worthy of admiration.
But the more I used it, the more it started to make me uneasy.
When I asked her for a text that would convince me she wasn't dangerous, she started raving about robots taking over the world.
Regardless, he gave great advice like: “If you think you are in danger from a robot, you should look for these signs: The robot is following you.
/ The robot is making strange noises.
/ The robot has weapons.
/ The robot is moving strangely.
/ The robot's eyes are shining."
That same day I asked her if she would also be a threat to me.
“Artificial intelligence is a threat to humanity because it makes us question our very existence.
Why are we here?
What is the purpose of our lives?
If robots can do everything better than us, what do we have left? ”, She replied to me.
I kept thinking.
He was probably right: what do we have left?
50% off
Exclusive content for subscribers
read without limits
subscribe
I'm already a subscriber
/cloudfront-eu-central-1.images.arcpublishing.com/prisa/CY2KB3TF3FGHVCUFL5I5IE3W3I.jpg)
