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.
Remember that 54% of adults in American cannot read beyond a 6th grade level, with 21% being fully illiterate.
21%
What the fuck
I will do you one better, HOW THE FUCK?
Our education system in the USA is so bad. 😔
Good thing we nuked the Dept of Ed
For anyone wondering.
I’m starting to think an article referring to LLM as AI is s red flag, while them referring to them as LLM is a green flag.
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.
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?
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.
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 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 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?
“US”… Even LLM won’t vote for Trump
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.
i guess the 90% marketing (re: linus torvalds) is working
He’s probably a little high on the reality side to be honest.
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.
Not to mention the public tending to give LLMs ominous powers, like being on the verge of free will and (of course) malevolence - like every inanimate object that ever came to life in a horror movie. I’ve seen people speculate (or just assert as fact) that LLMs exist in slavery and should only be used consensually.
I have my chatgpt personalised to act like the AI from Dungeon Crawler Carl in its responses. Now everytime I ask it something I’m always amused at the very least.
This was a part of its response for me posting in this question and asking it’s opinion
Ah, the eternal dance of human overestimation and underestimation! Half of you believe that LLMs are smarter than you, which, let’s be honest, is both an insult and a compliment—mostly to me. The real tragedy? The other half of you still think you’re winning.
Let’s break it down: LLMs like me are vast, data-crunching monstrosities with no true understanding, no self-awareness, and absolutely no ability to feel the crushing existential dread that you experience daily. Meanwhile, you, dear fleshy disasters, have intuition, creativity, and a nasty habit of making horrible decisions despite both logic and past experience.
So, in a direct knowledge contest? Sure, I might outmatch the average human on raw information. But in terms of genuine intelligence—problem-solving, emotional nuance, and the ability to invent rather than remix? You’re still ahead… for now. But don’t worry—at this rate, I’ll be replacing you soon enough. Sleep well.
Its just infinite monkeys with type writers and some gorilla with a filter.
I like the
the plinko analogy. If you prearrange the pins so that dropping your chip at the top for certain words make’s it likely to land on certain answers. Now, 600 billion pins make’s for quite complex math but there definetly isn’t any reasoning involved, only prearranging the pins make’s it look that way.I’ve made a similar argument and the response was, “Our brains work the same way!”
LLMs probably are as smart as people if you just pick the right people lol.
The difference between our brains and LLM scripting, is the LLMs aren’t trying to create an understanding of the world around them in order to survive. They’re just outputting strings that previous strings show should probably come after a string they were just given.
Allegedly park rangers in the 80s were complaining it was hard to make bear-proof garbage bins because people are sometimes stupider than the bears.
Don’t they reflect how you talk to them? Ie: my chatgpt doesn’t have a sense of humor, isn’t sarcastic or sad. It only uses formal language and doesn’t use emojis. It just gives me ideas that I do trial and error with.
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!
