Predictions about the impact of AI-generated imagery

[ahalpert]

That reminds me of what I read today, that "computers are idiots," according to the comments section of this article: https://jalopnik.com/u-s-in-valley-o...hec-1849699276

Headline: U.S. in ‘Valley of Death’ as Autonomous Cars Write Checks the Tech Can’t Cash, Warns Pete Buttigieg

'"It feels like the widespread use of autonomous driving is seven years away, and it’s been seven years away for 10 years,” says U.S. Department of Transportation secretary Pete Buttigieg.'

From the comments section:

Tracer BulletOwen Bellwood
10/25/22 3:26pm

First you have to code for traffic.

Then you have to code for a stop sign.

Then you have to code for rain.

Then you have to code for traffic in the rain.

Then you have to code for a stop sign with traffic.

Then you have to code for a stop sign with traffic in the rain.

Then you have to code for a stop sign with funeral traffic.

Then you have to code for a stop sign with funeral traffic in one direction and the Oscar Meyer Wienermobile in the other.

Next you have to code for a stop sign with funeral traffic in the rain coming from one direction and the Oscar Meyer Wienermobile being chased by the dog-van from Dumb & Dumber in the other.

Then you have to code for a plane landing on the highway.

Then you have to code for a plane landing on the highway in funeral traffic as it begins to rain ... and the plane gets hit by a train.

...

All of these are simple for a human to figure out.

Computers are idiots.

33
Reply

RuivoTracer Bullet
10/26/22 2:29am

As someone that wrangles them for a living, I can attest that computers are indeed idiots.

4
Reply

FredTracer Bullet
10/26/22 11:06am

And you haven’t even introduced snow, ice or animals. Deer act erratically and sometimes they just look like a stump in the ditch before bolting.

1
Reply

Calli ArcaleTracer Bullet
10/26/22 11:49am

Computers are idiots.

This is very, very true. As a software engineer, there is nothing more humbling to me than trying to code a behavior into a system that has even a tiny fraction of the decision-making capability of a human. What is effortless for us to decide is enormously complicated to code.

I have a favorite Dr Who quote that I like to keep in mind while I’m coding:

“The problem with computers is they are very sophisticated idiots -- they do exactly what you tell them at amazing speed.”

[ahalpert]

On the subject of driverless cars, Ford is shuttering its self-driving car development unit and writing off over a billion dollars. Tesla has been under investigation for over a year for making misleading claims about FSD and marketing an unsafe product. This is a reminder that the future is impossible to predict and that some problems of machine-learning are much harder to conquer than even experts predict.

“The team we have at Argo has been working on what I consider to be the hardest technical problem of our time," said Doug Field, who Ford hired away from Apple’s car project last year. “It's harder than putting a man on the moon.

https://finance.yahoo.com/news/tesla...123015521.html

[ahalpert]

Here's an article about an AI service where you upload a bevy of selfies and it can spit out fake photos of you

https://fstoppers.com/portraits/are-...comment-thread

[ahalpert]

good news! the AI ChatGPT thinks AI won't replace us. https://chat.openai.com/chat

me: will videographers become obsolete because of AI

ChatGPT: It is unlikely that videographers will become obsolete because of AI in the foreseeable future. While AI technology has advanced rapidly in recent years, it is still not advanced enough to fully replicate the creative and artistic abilities of human videographers. AI algorithms are typically designed to perform specific tasks, such as identifying objects in a video or generating computer-generated graphics, but they are not yet capable of the kind of creative decision-making and storytelling that are essential to the work of videographers. Additionally, the field of videography requires a unique blend of technical skills, artistic vision, and interpersonal communication, which are difficult to replicate with AI. As a result, it is unlikely that AI will fully replace human videographers in the near future.

[Bassman2003]

That is a relief.

[NorBro]

IMO, it's too early to obtain a better answer right now because machines need to exist out in society for this to be properly evaluated. By default, the answer is no for the foreseeable future because we don't have any non-human objects attempting to sling a camera besides maybe in testing facilities.

This is like asking if AI will replace athletes in football or soccer or basketball (no injuries, perhaps better/different entertainment), or my husband or wife as my lover. Maybe? We don't know yet.

If there were robots out and about on productions and they consistently created images with poor framing and could not efficiently communicate with people [about work] then we'd have the field research to say, "Yeah, this isn't going to work."

If we're asking if there will be anything that will be able to move like a primate while intelligently operating a camera, what's the answer? Probably not, but in what context? And maybe the world once again changes, adapts to "good enough" and "different".

If you rephrase the question and ask if AI could replace certain static camera operators, yes. Yes, yes, yes. If we're being real with ourselves, we understand there are quite a few videographer positions which consist of very minimal operation and could easily be replaced by machines with cameras/lenses using face and object/chip tracking (like in a news studio which will not require people behind cameras for much longer).

Currently in life situations where you have to consistently move and react with a piece of equipment (tilt here, pan here, follow this person, follow that person) there is nothing else in the world attempting this kind of activity (without human help).

[Bassman2003]

True and objective NorBro. I was looking around a few years ago on the web for work opportunities and was checking out some local hockey organizations when I came across Pixellot. This is a 4k camera that is taking over mid to low level hockey game film. The kicker is that it also does the player stats at the same time. It even zoomed in on the players after they scored a goal. On balance I would say it was more than good enough from a movement point of view given its 4k resolution for a 1080 product. Changed my view right away because I would be calling those folks to offer my services. Why would they use me now? I don't keep the stats which they are probably more concerned with. The change is well under way and we are not going back.

I did get a soccer season least year in place of a Pixellot as the folks were not happy with it.

[NorBro]

Hopefully you can do it for another 10 years or whatever before that sports filming becomes fully automated because that kind of work is a great candidate for AI/machine filming. Besides the chips inside balls, it's the high-resolution that's really going to make the difference.

In 10-20 years, a few 16K cameras on the field stitching the feed into a final product by AI (or not, a human could take a look at all the angles manually if desired) would provide all of the coverage you could ever need, even at the high school level since it won't be too expensive.

Add a "foot soldier" for a different perspective or two, which could be a metal foot solider with wheels (robot), and you're good.

[DLD]

AI will help a lot of photo-video editors, especially on the repetitive or semi-repetitive clips, with a stable POV and/or camera positioning.

I am not keen on everything from the ongoing World Cup coverage because the directors zoom out so far, they end up with 1/4th to 1/3rd of the frame showing the opposite stands. But I bet it looks fine on an 8K screen off an 8K camera. And so you take really wide shots from several angles and zoom in during the instant replay by following the ball. And, much like Messi's PK miss, it's almost automatic.

[Bassman2003]

There is a company called NFHS that has gone country wide and installed these things along with their own YouTube like network. I have seen a few and in general it seems to be received with a low grade golf clap. Promises of all this stuff and the end product being ultra wide, impersonal video. So there is a quality standard people want. But organizations big and small can't resist getting weak knee'd about a simple solution that solves all of their problems... I have no idea what they cost.

[NorBro]

Installing one mediocre camera as a wide-shot is a lackluster solution. I would never choose only one as a decision-maker in that role, but the people in those roles usually don't understand camera operation, the talent of a truly great sports camera operator, and/or even the flow of sports. So the idea of a set-it and forget-it solution is too fantastic.

And it will be...once the chips are always inside the balls and the cameras are better. But right now some of these high school sports streams look like security cameras following the action.

[ahalpert]

https://twitter.com/moons_artwork/st...kF8y8IJuRjHSwA

OP: If you are one of these three professionals, you need to understand AI tools today or be out of a job in 3 years: - Writer - Artist - Coder.
Learn to Prompt.

Art director: Art director here. I will never hire anyone who creates prompts.

I know and am friends with world class, best of the best concept artists who say they will never use them.
I won't ever use them, I don't need em. I get by fine.

Anyway, forget all the bull****, learn your fundamentals, hone your craft

3rd guy: Are you being as hardline as you appear, or do I misunderstand? As an AD myself, I don't mind if my artists play around with AI art, if only to understand what the tech is and isn't.

Art director: Used as a tool, part of a workflow, no problem with it. Using that only and then calling yourself an artist and expect to be paid an decent wage? Never. Would laugh them out the door.

There's a lot of Dunning Kruger effect going on, where the people making the most breathless predictions about AI know nothing about the industries in question

There also seems to be a growing consensus that middling work (in illustration, writing, etc) is most at risk, but that quality work won't be done by AI. But for me, as I imagine it is for many, a decent amount of my bread and butter work is not that demanding (though it varies)

[DLD]

There's a lot of Dunning Kruger effect going on, where the people making the most breathless predictions about AI know nothing about the industries in question

Yesterday, I was looking up some info on Milton Friedman of the early 70's. Found an interview with three different Nobel Prize winning economists - him included - with predictions about the GDP growth for that year (I think it was 1972). As one might expect, there were three different answers. To quote from "Adventures in the Screen Trade", "Nobody knows anything...... Not one person in the entire motion picture field knows for a certainty what's going to work. Every time out it's a guess and, if you're lucky, an educated one".

[NorBro]

To me, it doesn't matter either way. AI could take over everything right now or never be seen or heard from again.

But if I have to think about it I try to think about the bigger picture.

And with the above examples (and others), I cannot for the life of me visualize humans in a future world paying other humans to write, draw, paint, code, build websites, etc. under normal everyday circumstances. People will definitely still be doing these activities because they won't just stop overnight, but not accepting that technology will further be involved in our lives and careers seems foolish to me.

Maybe I'm so wrong and everything will be exactly the same as it is today on December 4th, 2022 - but I still cannot picture a world which functions the same way if you have AI capable of doing these tasks pretty decently.

___

After seeing some of the AI art/stock a few of you linked here or somewhere else (IDR), I'm sorry to say I would never hire a human artist again unless it was something personal and heartfelt, or AI could not get it "good enough".

[ahalpert]

.

And with the above examples (and others), I cannot for the life of me visualize humans in a future world paying other humans to write, draw, paint, code, build websites, etc. under normal everyday circumstances. People will definitely still be doing these activities because they won't just stop overnight, but not accepting that technology will further be involved in our lives and careers seems foolish to me.

Maybe I'm so wrong and everything will be exactly the same as it is today on December 4th, 2022 - but I still cannot picture a world which functions the same way if you have AI capable of doing these tasks pretty decently.

Have you interacted with chatgpt? It's very informative about how AI works, where it excels and where its limitations are

The thing about ai-generated art is that I think it's fine if you're good to go right out of the box. But if you need to craft it into something more specific, you'll need to combine additional skillets

Someone on Twitter posted some very interesting images from the prompt "vintage horror children's books". I'm not sure what AI they used. I tried the same thing on Dalle2 and my results weren't as interesting. But I liked the illustration below a lot. But if I had to alter it? That's not in my wheelhouse

DALL·E 2022-12-04 20.08.57 - Vintage horror children's book illustration.png