DEV Community

Cover image for An optimistic look at AI and our relationship with it
Gabriel Fernandes
Gabriel Fernandes

Posted on

An optimistic look at AI and our relationship with it

Today, just over a year since we were introduced to the world of AI, it's amazing to see how much this technology has evolved since then.

Mom reading with his child
Mom and child reading, generated by Midjourney

It's really impressive how much something so recent makes us question reality, whether what we see is real or not.

Something that cinema also motivated in its time, given the accounts of people running out of the rooms imagining that the train depicted would come out of the screen and advance on them.

Lumière Brothers’ 1895 Short ‘Arrival of a Train’

Lumière Brothers (1895) Short ‘Arrival of a Train’

Art, at least Western, for a long time was obsessed with reality, as artists studied for years to make portraits increasingly faithful to what was seen.

And this was the role of art until the advent of photography, which in turn took over any incumbency about portraying reality. And art initially had a certain prejudice with photography, but continued representing not so much realism, but now emotions and expressions, as in cubism or impressionism.

Self-portrait (1907) by Pablo Picasso

Self-portrait (1907) by Pablo Picasso.

Photography itself shows us some interesting aspects, such as, for example, a photo is nothing more than dealing with chance and setting up a composition with what is given or arranged in front of those lenses at that certain angle. Where even we take several pictures in order to choose the best one among them later.

Parallels can be easily drawn between photography and AI image generation, because generating images using any model we also deal with chance often, when it surprises us with random elements which we have to specify their absence or not. And of course, we generate several to choose the best one among them.

Both final products aim to convey a message, whatever it may be, and all necessary means will be called upon to achieve a certain end.

But one thing that differs the two, and which is one of the highest points in my opinion, is:

The ability that AI has to shape something that before we could only imagine. Where, in a way, it is expanding our imagination and also gradually modifying our view of reality.

It's interesting to see how AI has been used in the corporate world, where in sectors that we once thought were creative and therefore without the possibility of the machine having any space, we already see processes that can and are being automated and replaced. Which means we will have more time for other tasks.

robot thinking
Robot working on computers, generated by Midjourney

But what tasks would those be?

Ok, AI can automate things, but what comes before this process, what comes after? We have personality, everything that is exchanged between human beings.

The most advanced AI can very well write a code, but who will say how the code should be? Who will dictate the necessary parameters and references?

When we go to the dentist we don't get there and ask him to take out the tooth that hurts, but rather, we get there, show the tooth, and he analyzes and tells us what we need.

A good architect helps the client understand the best choice among alternatives, and sometimes shows the solution to problems the client didn't even know they had.

A while ago I remember a certain meme circulating on the internet

Tweet post joking about IA getting our jobs
Tweet on X, 2024

And I fully agree with it, not because customers are ignorant and don't know what they want, but because the best solution will always come from the one who knows the problem best and has enough background to say exactly what is needed, and what is not, according to their experiences. The most important thing will be this empathic connection and the support offered to those who need it.

How AI can free us from certain frustrations

These days I remember asking what a team partner was doing to make conversation and he told me he was doing such a service in RUST, at the time I was already surprised because he had never mentioned that he knew this language to me and was already building a complete solution in it. Then he showed me how he was learning, how since he knew a lot about JS and Node he wrote what he wanted in AI and asked it to draw parallels with the language he dominated.

I thought that was brilliant, because if we didn't have AI he would probably have to spend a much longer time on the learning curve, sometimes from scratch in RUST and take a much longer time to do what he wanted with the risk of getting demotivated and frustrated along the way.

So for the first time in the world we have the opportunity to learn a certain thing, in a personalized way, aligned with our individual method of learning.

Where else would a person who, "only learns" something if it is explained to her in the way of speaking of Master Yoda, learn so easily to build an API in python for example??

screenshot of a gpt requesting a teaching in Yoda's way to talk
GPT request, 2024

In all technology adopted en masse by society, as in the case of Social Networks, we see their clearly both positive and negative impacts. If on one hand they aided access to misinformation, on the other they gave space to many narratives previously silenced by hegemonic media.

And as today we live in a society that frequently revisits its moral values which are constantly changing, it is very important that we understand the power of what we are generating through these AI tools, as these results can often be biased, since they are responses from a certain database, which can also end up being influenced by its products.

My perspective for the future does not try to be prophetic in any way, saying which sectors will be decimated by AI if any, but rather having to follow a path of knowing what we can do from then on, where I believe that developing a critical sense was not and will not be something in vain; because that way we will have more property to write, choose references, parameters and judge as many times as necessary the result of our requests.

In the end, AI's will be what society wants them to be.

Arnold Schwarzenegger smilling at the camera in Terminator of the future

Thinking about that famous phrase:

"Talent is hitting a target that no one hits, Genius is hitting a target that no one had seen"

How many new targets are exposed by the AI's flashlight, since that today, more than ever, we are able to easily expand our intellectual horizons?

__

I had the idea to write this after spending a few weeks actively seeking out and consuming a lot of content on the subject through publications and podcasts. To better internalize what I was absorbing, improve my writing, and expand my vocabulary, I decided to return to writing, but this time in a more free-form manner than when I used to post on LinkedIn, which had character limits and so on...

Feel free to comment below with any insights you may have had while reading this article. It will be a pleasure to read each one!

Top comments (2)

Collapse
 
filipedev6 profile image
Filipe Rodrigues

I liked this post

Collapse
 
seufernandez profile image
Gabriel Fernandes

Thanks, I really appreciated :)