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.
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.
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.
21%
What the fuck
I will do you one better, HOW THE FUCK?
People can improve literacy in adulthood if they try.
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.
Nearly half of llm users are dumber than they seem
Only half?
Yeah thereabouts
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.
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.
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?
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
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?
I try not to think about them, honestly. (งツ)ว
you’re a healthier person than I.
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.
When talking about a large, regularly distributed population, there effectively IS no difference
There might be no difference. In memes or casual conversation the difference usually doesn’t matter, but when thinking about important things like government policy or medical science, the difference between mean and median is very important - which is why they both exist.
-
A joke is definitely casual conversation
-
Mathematically, the difference becomes increasingly statistically insignificant as your population size increases. Sure maybe there’s a few niche cases where a hundred-thousandth of a percent difference matters, but that’s not even worth bringing up.
-
The only reason any of you even bring it up is to try and sound smart in a pedantic, “ackshually” way.
Ironically your whole comment here is an elaborate “ackshually”.
This whole comment chain was me shutting down an “ackshually” with an even better one.
If you’re gonna be an annoying pedantic dick, you better be RIGHT, or someone else will be an even more annoying pedantic dick to you.
-
Not in all cases. When I teach mean, median and mode, I usually bring up household income. Mean income is heavily skewed by outliers (billionaires), median is a more representative measure.
I guess that’s your “regularly distributed” bit, but a lot of things aren’t regularly distributed.
IQ is though
IQ is also garbage when it comes to the validity of what it claims to measure.
Fair, but you could just say “intelligence” generically instead.
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.
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.
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.
i guess the 90% marketing (re: linus torvalds) is working
He’s probably a little high on the reality side to be honest.
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!
“US”… Even LLM won’t vote for Trump
