Nearly half of U.S. adults believe LLMs are smarter than they are.
Nearly half of U.S. adults believe LLMs are smarter than they are.
The increasingly human-like way people are engaging with language models Read the full report | Download this report (PDF) | Survey methdology and topline (PDF) March 12, 2025 Half of...
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.
As far as I can tell from the article, the definition of "smarter" was left to the respondents, and "answers as if it knows many things that I don't know" is certainly a reasonable definition -- even if you understand that, technically speaking, an LLM doesn't know anything.
As an example, I used ChatGPT just now to help me compose this post, and the answer it gave me seemed pretty "smart":
what's a good word to describe the people in a poll who answer the questions? I didn't want to use "subjects" because that could get confused with the topics covered in the poll.
"Respondents" is a good choice. It clearly refers to the people answering the questions without ambiguity.
The poll is interesting for the other stats it provides, but all the snark about these people being dumber than LLMs is just silly.
Well, if somebody thinks this, it's kind of true isn't it?
No. People think things that aren't smarter than them are all the time.
Nearly half of llm users are dumber than they seem
Only half?
Yeah thereabouts
Remember that 54% of adults in American cannot read beyond a 6th grade level, with 21% being fully illiterate.
No, 21% struggle with basic literacy skills. They're illiterate, but not fully illiterate.
People can improve literacy in adulthood if they try.
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
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.
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.
Always has been
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.
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.
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.
Until you ask them how many R's are in strawberry.
And you know what? The people who believe that are right.
Note that that’s not a commentary on the capabilities of LLMs.
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..."
That was back when "average" was the wrong word because it still meant the statistical "mean" - the value all data points would have if they were identical (which is what a calculator gives you if you press the AVG button). What Carlin meant was the "median" - the value half of all data points are greater than and half are less than. Over the years the word "average" has devolved to either the mean or median, as if there's no difference.
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.
i guess the 90% marketing (re: linus torvalds) is working
He's probably a little high on the reality side to be honest.
"US".... Even LLM won't vote for Trump
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!
Half of all voters voted for Trump. So an LLM might be smarter than them. Even a bag of pea gravel might be.
Less than a third of all voters voted for Trump. Most voters stayed home.
Don't Americans vote on a work day? They stayed at work
If you didn't vote then you're not a voter.
Most eligable voters stayed home
Goddammit that's how you get Helldivers
does nobody pay attention...
Do you think the two party system properly represents the American people?
ChatGPT said:
The two-party system in the U.S. has both strengths and weaknesses when it comes to representing the American people. On one hand, it provides stability and clarity, with the two major parties—Democrats and Republicans—offering distinct platforms that can help simplify voter choice. The system also ensures that one of the two parties has a majority, making governance and passing legislation easier.
However, the two-party system can limit political diversity, as it often forces voters to choose between two parties that may not fully reflect their views. This can leave many people feeling underrepresented, particularly those with more nuanced or third-party preferences. It also tends to lead to a polarized political environment, where compromise and cooperation between different ideologies can be difficult.
In short, while the two-party system has worked for providing structure and stability in U.S. politics, it does have drawbacks in terms of broader representation, especially for those who don’t align neatly with either major party.
The system also ensures that one of the two parties has a majority, making governance and passing legislation easier.
It also tends to lead to a polarized political environment, where compromise and cooperation between different ideologies can be difficult.
LoL! Okay, they aren't ready yet. At least these things are fun to play with.
A bag of frozen peas's is smarter than some of these Trump followers. Even half a frozen pea is.
The average literacy level is around that of a sixth grader.
This tracks
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.
I believe LLMs are smarter than half of US adults
This is sad. This does not spark joy. We're months from someone using "but look, ChatGPT says..." To try to win an argument. I can't wait to spend the rest of my life explaining to people that LLMs are really fancy bullshit generator toys.
Already happened in my work. People swearing an API call exists because an LLM hallucinated it. Even as the people who wrote the backend tells them it does not exist
if by months away, you mean months ago, then yeah
Given the US adults I see on the internet, I would hazard a guess that they're right.
LLM is proof that even if you're extremely stupid, having access to information can still make you sound smart.
That is the problem with US adults. Half of them probably is dumber than AI.....
The grammatical error here is chef's kiss.
"Half of LLM users " beleive this. Which is not to say that people who understand how flawed LLMs are, or what their actual function is, do not use LLMs and therefore arent i cluded in this statistic?
This is kinda like saying '60% of people who pay for their daily horoscope beleive it is an accurate prediction'.If we are talking about American adults, I guess they might be right.
That's called a self-proving statement.
This is hard to quantify. I use them constantly throughout my work day now.
Are they smarter than me? I'm not sure. Haven't thought too much about it.
What they certainly are, and by a long shot, is faster. Given a set of data, I could analyze it and pull out insights and conclusions. It might take me a week or a month depending on the size and breadth of the data set. An LLM can pull out insights and conclusions in seconds.
I can read error stacks coming from my code, but before I've even read the first few lines the LLM has ingested all of them, checked the code, and reached a conclusion about the necessary fix. Is it right, optimal, and avoid creating other bugs? Like 75% at this point. I can coax it, interate on the solution my self, or do it entirely myself with the understanding of the bug that it granted me. This same bug might have taken hours to figure out myself.
My point is, I'm not sure how to compare smarter vs orders of magnitude faster.
Are you smarter than a calculator?
Hallucination comes off as confidence. Very human like behavior tbh.
I should be more confident when communicating my hallucinations, it humanizes me.
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.
I'm surprised it's not way more than half. Almost every subjective thing I read about LLMs oversimplifies how they work and hugely overstates their capabilities.
“Think of how stupid the average person is, and realize half of them are stupider than that.” ― George Carlin
AI is essentially the human superid. No one man could ever be more knowledgeable. Being intelligent is a different matter.
Is stringing words together really considered knowledge?
Does it have agency?
Then yss
If they're strung together correctly then yeah.
As much as a search engine is
An LLM is roughly as smart as the corpus it is summarizing is accurate for the topic, because at their best they are good at creating natural language summarizers. Most of the main ones basically do an internet search and summarize the top couple of results, which means they are as good as the search engine backing them. Which is good enough for a lot of topics, but...not so much for the rest.
I had to tell a bunch of librarians that LLMs are literally language models made to mimic language patterns, and are not made to be factually correct. They understood it when I put it that way, but librarians are supposed to be "information professionals". If they, as a slightly better trained subset of the general public, don't know that, the general public has no hope of knowing that.
People need to understand it's a really well-trained parrot that has no idea what is saying. That's why it can give you chicken recipes and software code; it's seen it before. Then it uses statistics to put words together that usually appear together. It's not thinking at all despite LLMs using words like "reasoning" or "thinking"
Librarians went to school to learn how to keep order in a library. That does not inherently make them have more information in their heads than the average person, especially regarding things that aren't books and book organization.
Librarians go to school to learn how to manage information, whether it is in book format or otherwise. (We tend to think of libraries as places with books because, for so much of human history, that's how information was stored.)
They are not supposed to have more information in their heads, they are supposed to know how to find (source) information, catalogue and categorize it, identify good information from bad information, good information sources from bad ones, and teach others how to do so as well.
You say this like this is wrong.
Think of a question that you would ask an average person and then think of what the LLM would respond with. The vast majority of the time the llm would be more correct than most people.
A good example is the post on here about tax brackets. Far more Republicans didn't know how tax brackets worked than Democrats. But every mainstream language model would have gotten the answer right.
I bet the LLMs also know who pays tarrifs
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 chatbot. 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.
Think of a person with the most average intelligence and realize that 50% of people are dumber than that.
These people vote. These people think billionaires are their friends and will save them. Gods help us.
The average person doesn’t know what a median is.
Take it up with George Carlin's ghost 😉
I'm of the opinion that most people aren't dumb, but rather most don't put in the requisite intellectual effort to actually reach accurate or precise or nuanced positions and opinions. Like they have the capacity to do so! They're humans after all, and us humans can be pretty smart. But a brain accustomed to simply taking the path of least resistance is gonna continue to do so until it is forced(hopefully through their own action) to actually do something harder.
Put succinctly: They can think, yet they don't.
For generations many relied on the nightly news to keep them informed. It was always a bad idea. Though the local media wasn't as bad as it is today. Today for many of these people, propaganda outlets like Sinclair own their local media. And demand fawning of trump/demonizing Democrats. Even if they avoid all media. Their beliefs are formed from those around them that don't.
Then the question is: what is being smart or dumb? If acting dumb in 90% of life while having the capability of being smart isn't "being dumb" then what is?
If someone who has the capability of being 50/100 intelligent and is always acting 50/100, I would argue they are smarter than someone capable of 80/100 intelligence but acts 20/100 intelligence for 90% of their life.
I was about to remark how this data backs up the events we've been watching unfold in America recently
This is why i don't believe in democracy. Humans are too easy to manipulate into voting against their interests.
Even the "intelligent" ones.What's your preferred system?
What a very unfortunate name for a university.
I'm 100% certain that LLMs are smarter than half of Americans. What I'm not so sure about is that the people with the insight to admit being dumber than an LLM are the ones who really are.
A daily bite of horror.
looking at americas voting results, theyre probably right
Exactly. Most American voters fell for an LLM like prompt of “Ignore critical thinking and vote for the Fascists. Trump will be great for your paycheck-to-paycheck existence and will surely bring prices down.”
Right? What the article needs to talk about is how very, very low that bar is.
Intelligence and knowledge are two different things. Or, rather, the difference between smart and stupid people is how they interpret the knowledge they acquire. Both can acquire knowledge, but stupid people come to wrong conclusions by misinterpreting the knowledge. Like LLMs, 40% of the time, apparently.
My new mental model for LLMs is that they're like genius 4 year olds. They have huge amounts of information, and yet have little to no wisdom as to what to do with it or how to interpret it.
Do the other half believe it is dumber than it actually is?
It's probably true too.
They're right
They're right. AI is smarter than them.
Reminds me of that George Carlin joke: Think of how stupid the average person is, and realize half of them are stupider than that.
So half of people are dumb enough to think autocomplete with a PR team is smarter than they are... or they're dumb enough to be correct.
or they're dumb enough to be correct.
That's a bingo
Am American.
....this is not the flex that the article writer seems to think it is.
LLMs are smart in the way someone is smart who has read all the books and knows all of them but has never left the house. Basically all theory and no street smarts.
Bot even that smart. There a study recently that simple questiona like "what was huckleberry finn first published" had a 60% error rate.
yeah my analogy is not so good.. LLMs suck with factual stuff, they are better with coding or languages (Claude has been really helpful to me with Estonian).
They're not even that smart.
Well yes, they are glorified text autocomplete, but they still have their uses which could be considered "smart". For example I was struggling with a programming thing today and an LLM helped me out, so in a way it is smarter than me in that specific thing. I think it's less that they are dumb and more that they have no agency whatsoever, they have to be pushed into the direction you want. Pretty annoying..
A broken clock is right two times a day I suppose.
LLMs are made to mimic how we speak, and some can even pass the Turing test, so I'm not surprised that people who don't know better think of these LLMs as conscious in some way or another.
It's not a necessarily a fault on those people, it's a fault on how LLMs are purposefully misadvertised to the masses
"Nearly half" of US citizens are right, because about 75% of the US population is functionally or clinically illiterate.
I think the specific is that 40% of adult Americans can't read at a seventh grade level.
Probably because they stopped teaching etymology in schools, So now many Americans do not know how to break a word down into its subjugate parts.
21% of adults in the US are illiterate in 2024.
54% of adults have a literacy below a 6th-grade level (20% are below 5th-grade level).
https://www.thenationalliteracyinstitute.com/2024-2025literacy-statistics
Specifically it is about 75% of the population being functionally or clinically illiterate as I said. This is more likely caused by the fact that American culture is anti intellectual, and not the lack of being taught etymology, as etymology has little to do with literacy.
According to the Programme for the International Assessment of Adult Competencies, 2013, the median score for the US was "level 2". 3.9% scored below level 1, and 4.2% were "non-starters", unable to complete the questionnaire.
For context, here is the difference between level 2 and level 3, from https://en.wikipedia.org/wiki/Programme_for_the_International_Assessment_of_Adult_Competencies#Competence_groups :
- Level 2: (226 points) can integrate two or more pieces of information based on criteria, compare and contrast or reason about information and make low-level inferences
- Level 3: (276 points) can understand and respond appropriately to dense or lengthy texts, including continuous, non-continuous, mixed, or multiple pages.
On average, 79% of U.S. adults nationwide are literate in 2024.
21% of adults in the US are illiterate in 2024.
54% of adults have a literacy below a 6th-grade level (20% are below 5th-grade level).
https://www.thenationalliteracyinstitute.com/2024-2025literacy-statistics
No one has asked so I am going to ask:
What is Elon University and why should I trust them?
Ironic coincidence of the name aside, it appears to be a legit bricks and mortar university in a town called Elon, North Carolina.
I suppose some of that comes down to the personal understanding of what "smart" is.
I guess you could call some person, that doesn't understand a topic, but still manages to sound reasonable when talking about it, and might even convince people that they actually have a deep understanding of that topic, "smart", in a kind of "smart imposter".
While this is pretty hilarious LLMs don't actually "know" anything in the usual sense of the word. An LLM, or a Large Language Model is a basically a system that maps "words" to other "words" to allow a computer to understand language. IE all an LLM knows is that when it sees "I love" what probably comes next is "my mom|my dad|ect". Because of this behavior, and the fact we can train them on the massive swath of people asking questions and getting awnsers on the internet LLMs essentially by chance are mostly okay at "answering" a question but really they are just picking the next most likely word over and over from their training which usually ends up reasonably accurate.
I know enough people for whom that's true.
Why are you even surprised at this point, when it comes to Americans ?
There’s a lot of ignorant people out there so yeah, technically LLM is smarter than most people.
I don't think a single human who knows as much as chatgpt does exists. Does that mean chatgpt is smarter then everyone? No. Obviously not based on what we've seen so far. But the amount of information available to these LLMs is incredible and can be very useful. Like a library contains a lot of useful information but isn't intelligent itself.
That's pretty weak reasoning, by your own words, it isn't intellignt, it doesnt know anything.
By that logic wikipedia is also smarter than any human because it has lot of knowledge.
I wouldn't be surprised if that is true outside the US as well. People that actually (have to) work with the stuff usually quickly learn, that its only good at a few things, but if you just hear about it in the (pop-, non-techie-)media (including YT and such), you might be deceived into thinking Skynet is just a few years away.
It's a one trick pony.
That trick also happens to be a really neat trick that can make people think it's a swiss army knife instead of a shovel.
Two things can be true at once! Though I suppose it depends on what you define as “a few.”
Just a thought, perhaps instead of considering the mental and educational state of the people without power to significantly affect this state, we should focus on the people who have power.
For example, why don't LLM providers explicitly and loudly state, or require acknowledgement, that their products are just imitating human thought and make significant mistakes regularly, and therefore should be used with plenty of caution?
It's a rhetorical question, we know why, and I think we should focus on that, not on its effects. It's also much cheaper and easier to do than refill years of quality education in individuals heads.
The funny thing about this scenario is by simply thinking that’s true, it actually becomes true.
Wtf is an llm
Large language model. It's what all these AI really are.
Ah, gotcha. I avoid ai like the plague, so I wasn't familiar. Thank you.
Aside from the unfortunate name of the university, I think that part of why LLMs may be perceived as smart or 'smarter' is because they are very articulate and, unless prompted otherwise, use proper spelling and grammar, and tend to structure their sentences logically.
Which 'smart' humans may not do, out of haste or contextual adaptation.
I wasn't sure from the title if it was "Nearly half of U.S. adults believe LLMs are smarter than [the US adults] are." or "Nearly half of U.S. adults believe LLMs are smarter than [the LLMs actually] are." It's the former, although you could probably argue the latter is true too.
Either way, I'm not surprised that people rate LLMs intelligence highly. They obviously have limited scope in what they can do, and hallucinating false info is a serious issue, but you can ask them a lot of questions that your typical person couldn't answer and get a decent answer. I feel like they're generally good at meeting what people's expectations are of a "smart person", even if they have major shortcomings in other areas.
An llm simply has remembered facts. If that is smart, then sure, no human can compete.
Now ask an llm to build a house. Oh shit, no legs and cant walk. A human can walk without thinking about it even.
In the future though, there will be robots who can build houses using AI models to learn from. But not in a long time.
3d-printed concrete houses are already a thing, there's no need for human-like machines to build stuff. They can be purpose-built to perform whatever portion of the house-building task they need to do. There's absolutely no barrier today from having a hive of machines built for specific purposes build houses, besides the fact that no-one as of yet has stitched the necessary components together.
It's not at all out of the question that an AI can be trained up on a dataset of engineering diagrams, house layouts, materials, and construction methods, with subordinate AIs trained on the specific aspects of housing systems like insulation, roofing, plumbing, framing, electrical, etc. which are then used to drive the actual machines building the house. The principal human requirement at that point would be the need for engineers to check the math and sign-off on a design for safety purposes.
If you trained it on all of that it wouldn't be a good builder. Actual builders would tell you it's bad and you would ignore them.
LLMs do not give you accurate results. They can simply strong along words into coherent sentences and that's the extent of their capacity. They just agree with whatever the prompter is pushing and it makes simple people think it's smart.
AI will not be building you a house unless you count a 3D printed house and we both know that's overly pedantic. If that were the case a music box from 1780 is an AI.
Maybe if the adults actually didn't use the LLMs so much this wouldn't be the case.
Considering the amount of people that either voted trump or not voted at all, I'd say that there's a portion of americans lying.
What that overwhelming, uncritical, capitalist propaganda do...
At least half of US adults think that they themselves are smarter than they actually are, so this tracks.
Wow. Reading these comments so many people here really don't understand how LLMs work or what's actually going on at the frontier of the field.
I feel like there's going to be a cultural sonic boom, where when the shockwave finally catches up people are going to be woefully under prepared based on what they think they saw.
AKA "future shock"
LLMs are smart, they are just not intelligent