this post was submitted on 27 Jan 2024
122 points (90.7% liked)
Arch Linux
7516 readers
1 users here now
The beloved lightweight distro
founded 4 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
Not copy pasting random commands you are not 100% sure about is basic terminal literacy
Online forums can give bad advice, but this is just next level bad. GPT truly has no remorse.
It's a language model, I still don't understand why people expect it to always give correct answers. You asked for some code, it gave you some code, I don't see what is the problem, it worked as it should, and it's astonishing that current technology can do this.
I also don't like the term "Artificial Intelligence", we should call these things LLM, or ML as Machine Learning.
LLMs are a specific implementation of ML, which is a field of AI. It's all still AI
I think the topic should change from A.I. to machines or smth.
Doesn't matter if its a simple bot regulating something simply or a LLM. For some dumb reason the are both called A.I.
Real Artificial Intelligence doesn't exist yet.
Because they are both AI. Artificial intelligence and Artificial General intelligence are not the same thing. AI is an entire field of computer science dating back to the very beginnings.
People expect the current models to be sentient, conscious etc. but we’re still very far from that. All of our ML creations are still very narrow in their scope.
It gives a lot of plainly wrong answers, including in fields where one would expect it to excel (basic physics, for instance).
Why would a program that outputs sudorandom strings based on how often they appeared after the string before excel at basic physics, even if it did have most of the text side of the internet fed into it to determine how often string b follows string a? It’s a miracle of programing and self reinforcement that it can form a sentence at all.
It also gives a lot of right answers.
The point is not to blindly believe either and use it as a tool to further research.
Works with online forums and real life interactions too. Just because someone said or wrote something doesn’t automatically make it reliable.
So you're saying not to blindly trust everything written on a forum is true. Which means I shouldn't trust that anything on Lemmy is true. Which means your comment on Lemmy saying not to trust everything on forums to be true must be false. Therefore everything including your comment is true, which means everything is false which means everything must be true...
It's all become quite clear! I...need a nap
LOL
But seriously though: ~~Must be false~~ -> may be false
Some times it’s difficult to tell.
Meh, we call people intelligent and they give wrong answers confidently too. It’s not AI in the traditional sense, but AI has now come to mean LLM for non tech literate users. Language evolves. We don’t need to fight it.
How will you call the "AI in traditional sense" when we finally arrive to that? You can't call that AI, because that's LLM now.
I'm not against the natutral development of languages, I simply don't like mislabeling things.
Already AI is categorized. Likely it will be called true AI or complex AI or something similar. Like any technology, eventually the newer version will replace the old and it will just be called AI again.
What people mean by AI has changed. When Optical Character Recognition was new, that was considered AI. Nowadays it’s so common that it’s nothing special any more. When people talk about AI in the 2020s, they usually exclude OCR from the definition.
It will likely either be called some different term like NPA (Neural Processing Agent which I just made up), or it will just get the AI term again and the colloquialism for LLM's being known as AI will fade. It happens for all sorts of other things, and context also depends a lot. CPU used to be a colloquialism for computer, now CPU's themselves are more commonly used and so the term has faded, outside of random SEO sales sites.
It's not really mislabeling, it is colloquial language. Society has ebbs and flows, the only thing ever wrong with these IMO is a failure of communication due to poor contextual understanding (and delivery). If something is explained in a proper sentence, it usually doesn't much matter if you're using academic language or colloquial terms. That is to say, you are absolutely right - the distinction is important, but we have the ability to code switch between average conversations that still get the point across and ones which use the exact specific terms and nitpick every single wrong word and why...
Also, I believe it's currently called AI specifically because they are masking it as an artificial intelligence. (Not that that makes it what the term was first coined to be) Bard, a named code execution using LLM's trying to speak in natural language presenting information... It's artificial, it's intelligence, it's presenting itself as such! /s-ish (this isn't what I believe, it's what I believe is how it's being presented). This is more personified than ChatGPT or Bing Chat, but it's not the first time we've had Chatbots get called AI.
Moreover, I think the term artificial intelligence is fairly broad from a lingual perspective and extremely narrow from its creators point of view (which was extremely similar to how current "AI" functions today - input image recognition output responses, that machine just happened to be analog and ours are digital). So generative AI is almost more accurately called AI than anything else, especially LLM models. But that's kind of limiting too considering the vast amount of science fiction that has explored AI that is explicitly more than being able to recognize whether the presented image is a circle or a square.
I'm with you though, we should call LLM's as they are, generative imaging is just that, but if they are put together and I can have what feels like a conversation and it can show me pictures of what it's referencing... I'm not going to nitpick the nuances of what this AI is comprised of, I'm just going to call it an AI. What the internal functions are can change, it's still... AI. Just like how if I were in front of security cameras and I was talking with a coworker about how there's a technology that can track moving objects and label various things, I'm likely not going to use the specific terms that are compromised of algorithms referencing image models... It's an AI that can identify things from live video. (mythicalAI for more on that)
So, all in all I think it really comes down to a contextual presentation and the fact that artificial intelligence, by nature, is a series of constructions. It seems to me that there inherently cannot be a single "AI" because we have shown that there are a vast number of ways to reach artificial intelligences. And what AI "really is" changes based on who wrote about it or who manufactured it.
Well, LLMs base their answers on content scraped from the web and those same online forums.
I guess, one day GPT will tell me to run rm -rf /* because it read that on an online forum somewhere.