Generative AI is overrated, long live old-school AI !
TLDR; Don't be dazzled by generative AI's creative charm! Predictive AI, though less flashy, remains crucial for solving real-world challenges and unleashing AI's true potential. By merging the powers of both AI types and closing the prototype-to-production gap, we'll accelerate the AI revolution and transform our world. Keep an eye on both these AI stars to witness the future unfold.
Throughout 2022, generative AI captured the public’s imagination. Now that GPT-4 is out, the hype is poised to reach new heights.
With the late 2022 release(s) of Stable Diffusion, Dall-E2, and ChatGPT, people could engage with AI first-hand, watching with awe as seemingly intelligent systems created art, composed songs, penned poetry, and wrote passable college essays.
Only a few months later, some investors have become only interested in companies building generative AI, relegating those working on predictive models to “old school” AI.
However, generative AI alone won’t fulfill the promise of the AI revolution. The sci-fi future that many people anticipate accompanying the widespread adoption of AI depends on the success of predictive models. Self-driving cars, robotic attendants, personalized healthcare, and many other innovations hinge on perfecting “old school” AI.
(Score: 2, Funny) by shrewdsheep on Thursday March 16, @10:41AM
Tesla's self-driving AI is based on predictive models, you see. And it's bad. They should use generative AI instead to render the trip on the windshield. That would make for a much better experience.
(Score: 0) by Anonymous Coward on Thursday March 16, @12:38PM (1 child)
https://www.youtube.com/watch?v=qnHbGXmGJCM [youtube.com]
(Score: 0) by Anonymous Coward on Friday March 17, @01:18PM
MoFo, I'll show you an adversarial AI. Ping YouTube's favorite light transport researcher and tell him about this. [speculativeidentities.com] What a time to be alive... or not!
(Score: 2, Interesting) by Anonymous Coward on Thursday March 16, @04:01PM (1 child)
https://en.wikipedia.org/wiki/Cyc [wikipedia.org]
They've been at this for a good long while, here's one application (from the wiki link) that looked interesting to me:
(Score: 0) by Anonymous Coward on Friday March 17, @02:54AM
(Score: 0) by Anonymous Coward on Thursday March 16, @07:37PM
"I'm sorry Dave, I'm afraid I can't do that"
-HAL
(Score: 4, Funny) by DannyB on Friday March 17, @04:59PM
Me: Give me a sarcastic explanation of why I should program in Perl.
Chat GPT3:
Oh, where do I begin? Well, if you want to waste your time learning a language that's obscure and out of date, then Perl is the way to go. And who wouldn't want to spend hours sifting through Perl's maze of cryptic syntax and jumbled code? It's like a fun little puzzle game, right? Plus, nothing beats the thrill of trying to debug a Perl program that's been inexplicably broken for days. And let's not forget the joy of writing code that's nearly impossible for anyone else to read, making you the only person capable of maintaining it. So, if you're looking for a headache-inducing, frustrating, and generally miserable programming experience, then Perl is definitely the language for you!
Me: Give me a sarcastic explanation of why I should program in Perl that sounds like a stoner.
Chat GPT3:
Duuuude, why program in Perl? Why not program in a language that makes you feel like you're on cloud nine? Perl is like the ultimate chill language, man. Its syntax is so funky and complex, it'll make you feel like you're in another dimension. And the best part is, you don't even need to understand what you're typing! Just let your fingers do the talking and watch the magic happen. Who needs readability and maintainability when you have Perl, bro? It's like a psychedelic trip for your computer. So, grab some munchies and start coding in Perl, you won't regret it.
How often should I have my memory checked? I used to know but...