I’ve been guilty of throwing the words “AI” around myself, but the more I hear the term nowadays, the more annoyed I get because there is no “AI” in these systems. Sure, they might be “Artificial”, but they certainly aren’t “Intelligent”! Not by any stretch of the word ….

https://www.washingtonpost.com/technology/2023/03/05/ai-voice-scam/

The actual story is worth reading to understand what kind of new scams and threats you can expect with these developing technologies, but I really do wish people would stop calling everything AI ….

#NotAI #Scams #TechHorrors

@EPluribusPlus Just getting the answers right doesn’t make something intelligent — you have to be able to critically evaluate facts and to be able to distinguish between things. These systems are not capable of that. Try coding with the help of a large language model for long enough and you’ll find that it gives you inventented answers.

If the system were truly ingelligent, it would know the difference between fact and fiction. So, while I respect your right to have your own opinion, I don’t believe it’s correct to say something is intelligent just because it can regurgitate facts, especially when it invents “facts” if it doesn’t have them.

@EPluribusPlus And that’s another thing I hate about how people approach machine learning systems — saying that they hallucinate. They do not hallucinate. They just give you fake information because they are just generators which put text together and are unable to distinguish between what is real and what is fake since they have no intelligence.

We really need to stop anthropomorphizing these systems 🙂 They are not people. Just systems which have been taught to recognise patterns but do not have the capability to reason about these patterns.

As for the animal kingdom, would you care to give some examples? I can’t comment on your point without knowing what you consider to be systemic failure in logic …

@EPluribusPlus And why would we want animals to be just like us? Also, do we know for a fact that they lack language, capacity to plan etc.? There are various counter-examples I can provide for each of those 🙂

Why does another species have to do things exactly the way we do or in a way we understand? Why are we so human-centric? 😛

@EPluribusPlus My question to you would be, why are we bringing in animals into the discussion? 🙂

The original question was whether what people call AI is actually intelligent. You seemed to think so. I don’t think so and mentioned that AI will just conjure information wholesale for you.

You countered with humans hallucinate too. (Though to be honest, these ML systems are not hallucinating — that’s just what some people have decided to call it — they are just generating information).

You also mentioned animals at this point. Now you mention “if we consider all animals to be intelligent that lowers the bar”. But my question is why do we need to bring animals into this at all?

Are current ML systems capable of reasoning? That probably would be what would qualify them to be called “intelligent” would be my guess. As far as I can tell, they are not capable of reasoning at this point. All they are capable of is looking at patterns and making decisions based on statistics.

This would probably be the same difference as a human who has learnt things by rote and is able to parrot back that information but cannot tell you the implications of that information beyond what they memorised. If they can’t draw inferences between two pieces of the information they’ve acquired and can only parrot it back at you, or worse, will invent stuff because they don’t know something, then that’s not intelligence 🙂