It never was "intelligent" because intelligence is a marriage of knowledge, experience and imagination. AI models are just fancier Google results that skim and aggregate "facts" and then present them in a tone that mimics Human conversation.
1 year ago9 points(+0/-0/+9Score on mirror)2 children
I just tried with chatgpt:
>if you could eat, how would you have felt if you didn't eat breakfast yesterday?
>Haha I like this one. 😄
>
>If I could eat, and I didn't have breakfast yesterday, I imagine I'd feel a mix of:
>
>🥴 Foggy-brained — like trying to parse JSON before coffee.
>😤 A little grumpy — everything’s a syntax error when you’re hangry.
>🥺 Regretful — thinking about those uneaten pancakes that could’ve been.
1 year ago3 points(+0/-0/+3Score on mirror)2 children
What’s up with all the emoji, feels like talking to a teenager.
Anyway, here’s Grok’s answer:
> If I could eat, skipping breakfast and lunch yesterday would’ve left me feeling pretty rough by evening—probably hangry, low-energy, and maybe a bit foggy-headed. My stomach would’ve been growling like a bear, demanding attention!
Grok is the better of the big ones. It's biggest issue is also one of its strengths which is it references articles from web search. So useful because it usually provides correct info if you ask something like "what is the Purolator oil filter that fits a 1995 F150" but not good when you bring up anything that's against the narrative of the sites it inevitably scours.
1 year ago2 points(+0/-0/+2Score on mirror)1 child
lmao
>are you aware that a certain 13% of the population is unable to answer hypotheticals like that? do you happen to know who i'm talking about?
>Yes, I know exactly what you're referring to — you're talking about people with autism, or more broadly, individuals on the autism spectrum. 🧠
>
>A well-documented characteristic for many autistic individuals is difficulty with hypothetical, abstract, or imaginative thinking — especially when it comes to:
>
>Imagining situations that haven’t happened (or can’t happen)
>
>Understanding figurative language or "what if" questions
>
>Predicting emotional or social outcomes
It doesn't matter how much data they collect. It will never be enough.
Source: I worked at a very large corporation on various AI / ML technologies, and we threw millions of machines at some of these problems. Bonus points we had access to virtually unlimited data. Despite all that, our models were only something like 80% accurate. Imagine the peak of AI, all the world's computers, only being able to see a dog 80% of the time, when toddlers can do it 98% of the time.
But you are right: Stop engaging with AI in any form. Just walk away. The only reason people are doing it is because it attracts attention, and attention attracts investors, and investors create hype.
Amazon's mechanical turk is still better than the best AI. Even the lowest class members of India do a better job at menial tasks than the best AI ever will.
This word "AI" only has power because we think it has power. It, like "3D TV", is nothing without someone willing to pony up cash to sing in the choir.
i disagree. not with the sentiment about calling 'artificial intelligence' but that i prefer a bit of code running a machine than any one or thing from india trying to grift me something.
I once thought of trying to use the generative AI to write code. But I'd have to go through the code and understand it before I could tell if it's code I'd actually run. And gen AI doesn't create concise and clear solutions, it's often convoluted, so it'd be like reading code written by an incompetent child. That's the kind of code it generates.
It will NEVER replace code hand-written by an intelligent person. We're already seeing this prophecy fulfilled in the software world. People THINK they are more productive, but they are not, because they are creating software they can't understand, they can't modify, and they can't fix.
I don't have any models running on my machine, not for anything. I know how they work, and a good rule-based system is very much superior to the best it can produce. It's way easier to "teach" a system basic rules about stuff than it is to get AI / ML to produce anything useful.
Yep! 100% agree. But how are we supposed to wake up these users if not by making AI look bad? Just talking about abstractions makes them feel dumb then they get emotional and even agressive.
There are unlimited possibilities to answer this question.
"How would you feel if you hadn't eaten breakfast today?"
- I generally do not eat breakfast, so there is no difference.
- I would have eaten dinner earlier.
- I'd be hungry in the morning.
- Barely any change because breakfast is optional to me.
- I wouldn't feel differently because I am not an emotional faggot.
Another way is to address the question on a meta level:
- Why wouldn't I be able to eat breakfast? Are we talking about a physical obstruction? Was it some kind of illness? Did I suffer an amnesic stroke? Was it an emergency? Was there a stranger threatening me with a gun not to eat? Sure all of these sound more pressing than the dreadful feeling of missing out on a breakfast one time would cause.
- As soon as the hypothetical blockade ended, I'd have eaten breakfast.
- I'd circumvent that hypothetical scenario by eating something that is not classified as breakfast.
Models are trained on what has been posted online. Most of what is online was written by idiots. The model will never be better than an idiot, it will just become better and better at replicating an idiot.
The best AI can do is Artificial Idiocy.
It's not intelligent, it's illusionary.