- cross-posted to:
- technology@lemmy.zip
- cross-posted to:
- technology@lemmy.zip
Half of LLM users (49%) think the models they use are smarter than they are, including 26% who think their LLMs are “a lot smarter.” Another 18% think LLMs are as smart as they are. Here are some of the other attributes they see:
- Confident: 57% say the main LLM they use seems to act in a confident way.
- Reasoning: 39% say the main LLM they use shows the capacity to think and reason at least some of the time.
- Sense of humor: 32% say their main LLM seems to have a sense of humor.
- Morals: 25% say their main model acts like it makes moral judgments about right and wrong at least sometimes. Sarcasm: 17% say their prime LLM seems to respond sarcastically.
- Sad: 11% say the main model they use seems to express sadness, while 24% say that model also expresses hope.
You must log in or register to comment.
Well, if somebody thinks this, it’s kind of true isn’t it?
Remember that 54% of adults in American cannot read beyond a 6th grade level, with 21% being fully illiterate.
21%
What the fuck
Our education system in the USA is so bad. 😔
Nearly half of U.S. adults
Half of LLM users (49%)
No, about a quarter of U.S. adults believe LLMs are smarter than they are. Only about half of adults are LLM users, and only about half of those users think that.
to be fair they’re American and they’re LLM users, so for a selected group like that odds are they really are as stupid as LLMs.
LLMs don’t even think. Four year olds are more coherent. Given the state of politics, the people thinking LLMs are smarter than them are probably correct.
literally dogs are smarter and have more reasoning ability.
Than half of LLM users? Probably
also that, yes.
oh my god 49% of LLM users are pathologically stupid.
and still wrong.
Still better than reddit users…
where do you think these idiots spend their time?
Next you’ll tell me half the population has below average intelligence.
Not really endorsing LLMs, but some people…
pathologically stupid, and still wrong. yes.
They are. Unless you can translate what I’m saying to any language I tell you to on the fly, I’m going to assume that anyone that tells me they are smarter than LLMs are lower on the spectrum than usual. Wikipedia and a lot of libraries are also more knowledgeable than me, who knew. If I am grateful for one thing, it is that I am not one of those people whose ego has to be jizzing everywhere, including their perception of things.
The statement is “smarter”, not “possesses more information”. None of the things you listed (LLMs, libraries, Wikipedia, etc.) have any capacity to reason.
The only thing you’ve argued is that you are choosing one particular definition of smart, ignoring the one I was using, and going all Grammar Nazi into how that’s the only possible definition. As I’ve said, if I am grateful for one thing, it is that I am not one of those people whose ego is shallow enough to has /have to be jizzing everywhere, including their perception of things.
moron opens encyclopedia “Wow, this book is smart.”
If it’s so smart, why is it just laying around on a bookshelf and not working a job to pay rent?
If you don’t have a good idea of how LLM’s work, then they’ll seem smart.
Until you ask them how many R’s are in strawberry.
only boomers and tech-unsavy people think that.
unfortunately, no. when the concept of machine intelligence was first being explored, marvin minsky(I think)'s secretary used ELIZA, the basic fits-on-a-page. they said it was absolutely a person, that they were friends with it. he walked them through it, explained the code (which, again, fits on one page in a modern language. a couple punch cards back then, you can look at what looked at first glance like a faithful python port here). the secretary just would not believe him, INSISTED that it was a person, that it cared about them.
this was someone working around the cutting edge of the field, and being personally educated by one of those big ‘great man’ type scientists-and not one of the egotistical shithead ones who’d have been a garbage teacher.
“US”… Even LLM won’t vote for Trump
i guess the 90% marketing (re: linus torvalds) is working
He’s probably a little high on the reality side to be honest.
And you know what? The people who believe that are right.
Note that that’s not a commentary on the capabilities of LLMs.
They are right when it comes to understanding LLMs the LLM definitely understands LLMs better than they do. I’m sure an AI could have a perfect IQ test. But has a really hard time drawing a completely full glass of wine. Or telling me how many R’s are in the word strawberry. Both things a child could do.
It’s sad, but the old saying from George Carlin something along the lines of, “just think of how stupid the average person is, and then realize that 50% are even worse…”
If I think of what causes the average person to consider another to be “smart,” like quickly answering a question about almost any subject, giving lots of detail, and most importantly saying it with confidence and authority, LLMs are great at that shit!
They might be bad reasons to consider a person or thing “smart,” but I can’t say I’m surprised by the results. People can be tricked by a computer for the same reasons they can be tricked by a human.
So LLMs are confident you say. Like a very confident man. A confidence man. A conman.
You know, that very sequence of words entered my mind while typing that comment!
