I just started trying out GPT4 and DALLE2

I just started trying out GPT4 and DALLE2
by akarl (2023-03-25 13:39:32)

In reply to: I don't think that anyone who is not developing AI ... posted by Ofcr. Tim McCarthy

and I am dumbfounded. "Write a c++ program that uses openmp with 5 child processes to approximate pi. I want a confidence interval on the point estimate". And it works.

I had always joked with my kids about writing a picture book, and I used DALLE2 to generate some images and put a book out on the Kindle store. Probably took me 3 hours and it was worth the entertainment value for my kids. I linked one of the images which stated with the prompt "Norman Rockwell painting of kids wiping their hands on a wall." It generated a picture frame on the wall as well. I deleted the image inside the frame and asked for it to draw a "Norman Rockwell painting of an exasperated mother cleaning a wall"

Finally, I can't belive how well GPT4 can create poetry and songs according to given meters or styles.
"Write a rap ballad summarizing Dante's divine comedy and include a summary of the moral themes"

Verse 1:
Yo, let me tell you 'bout a journey to hell
Dante's Divine Comedy, it's a story to tell
A poet lost in the woods, unsure of his fate
Until Virgil came, and showed him the way

Chorus:
From the depths of hell to the highest heaven
Dante's journey took him through the seven
Circles of hell, where the sinners reside
And purgatory, where redemption can be found inside

Verse 2:
First circle, limbo, for those who died unbaptized
Then lust, gluttony, greed, and anger, all so despised
Heresy and violence, the sixth and the fifth
And treachery, the worst, the ninth circle abyss

Chorus:
From the depths of hell to the highest heaven
Dante's journey took him through the seven
Circles of hell, where the sinners reside
And purgatory, where redemption can be found inside

Verse 3:
In purgatory, the souls climb the mountain high
Repenting for their sins, before they can fly
Up to the paradise, where God's love abounds
And the ultimate reward, for those who turn their lives around

Chorus:
From the depths of hell to the highest heaven
Dante's journey took him through the seven
Circles of hell, where the sinners reside
And purgatory, where redemption can be found inside

Verse 4:
The moral of the story, is to live a life of grace
Avoiding sin and temptation, to stay in God's good graces
To repent for our mistakes, and seek redemption
And strive to live a life of love, and perfection

Chorus:
From the depths of hell to the highest heaven
Dante's journey took him through the seven
Circles of hell, where the sinners reside
And purgatory, where redemption can be found inside

Outro:
So let us all remember, Dante's Divine Comedy
And strive to live a life, that's both righteous and worthy
For in the end, it's not the wealth or fame we gain
But the love and grace of God, that will forever remain.

Click here for link at https://drive.google.com/file/d/1vw5XuheCfSVxDSV2u3VFjWcbRgB

Think about all the millions of people who have ...

... entrusted their and their families' futures to their computer science careers, upon the urging of pretty much every kind of educational and career authority out there, over the last 20 years. People currently in their 20s, 30s, 40s. Their careers could be eradicated, by the millions, within, what? Eighteen months? Two years? Hey, maybe five years.

Add the health care workers whom Gates and others believe will be "empowered" to "do other things." The architects and engineers. The logistics and accounting and production managers. The actors and models, the copywriters, the salespeople .... On and on and on, and it isn't going to take strong AGI to do it. It's only going to take the tools that are being rolled out, to the market, right now.

Regarding the timeline

I spent a lot of time a few years ago working on some applications of recurrent neural networks in Keras. These are a different architecture of neural network than used by GPT and DALLE, but they have a lot of similarities (as of 2017 it was the model structure used by Google translate). So I was able to get some insight into the potential of text and image analysis and generation. If you had asked me before I first looked at these programs a few weeks ago, I would have guessed that the kind of functionality I am already seeing when playing around would have been 10 years away. So I can't imagine what things will look like in 10 years.

There are still enough errors in the output to require expertise in sporting and fixing them, but even now this could represent a huge reduction in programming time just from getting the initial libraries and functions setup instantly while also minimizing typos and bugs.

The worst point in the transition will be when the AI

isn't reliable enough to get all the hard points, but the humans in the loop get lazy and stop being skeptical and stop looking for the "stupid AI, you missed..." things.

…becomes self aware and launches a nuclear attack. *

Nah - by that point, we'll be so sick of AI generated ads

for the AI generated models of the AI generated political candidates, KPOP boybands, and DiKToK social media influencers, we'll welcome the sweet, sweet thermonuclear annihilation.