- 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.
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?
Home-skoolin
Our education system in the USA is so bad. 😔
Good thing we nuked the Dept of Ed
No, 21% struggle with basic literacy skills. They’re illiterate, but not fully illiterate.
People can improve literacy in adulthood if they try.
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 the realize that 50% are even worse…”
Yeah but thats 50% on a bell curve. So think of the average person and that represents 68% of the population. Going 1 standard deviation lower 13% then lower is 2%. Numbers here are generalised*
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. What Carlin meant was the “median” - the value in the exact middle of the range of values. Over the years the word “average” has devolved to either the mean or median, as if they’re the same.
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.
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?
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.
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.
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.
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.
It’s like asking if you think a calculator is smarter than you.
„It‘s totally a lot smarter than I am, no way could I deliver (234 * 534)^21 as confidently!“
Are you suggesting my 90’s calculator is smarter than LLM’s?
Hard to compete with that 90s confidence 😎
“Think of how stupid the average person is, and realize half of them are stupider than that.” ― George Carlin
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
Of you didn’t vote then you’re not a voter.
Most eligable voters stayed home
A bag of frozen peas’s is smarter than some of these Trump followers. Even half a frozen pea is.
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.
LoL! Okay, they aren’t ready yet. At least these things are fun to play with.
"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 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.
Excellent. Personally I would try to make it emulate Marvin the Paranoid Android.
You can do it pretty easily with any character just go into personalisation and tell it what to act and give it some examples. You can even ask it to make the personality config for you. Works on the free one as well.
But yeah I’ve found it a lot more fun since.
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.
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.
LOL I remember a real life park ranger actually telling me this.
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.
Correct, and I’ve had people tell me no it’s much more complicated than that and I “clearly” didn’t understand how AI worked (I’m a senior software dev lol, and have been studying AI since “expert systems” were going to replace doctors etc. and revolutionize the world back in the late 80s). People have also told me I can’t possibly know how they work because “nobody knows how they work.” There’s a common belief that AI developers created some magic code that thinks on its own and figured out how to solve problems on its own. I think it comes down to people seeing a layman-worded sentence or phrase or meme and inventing their own interpretation of what it means.
That sure sounds like fox news connoisseurs.
Until you ask them how many R’s are in strawberry.
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.
The average literacy level is around that of a sixth grader.
This tracks
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.
It’s so weird watching the masses ignore industry experts and jump on weird media hype trains. This must be how doctors felt in Covid.
It’s so weird watching the masses ignore industry experts and jump on weird media hype trains.
Is it though?
I’m the expert in this situation and I’m getting tired explaining to Jr Engineers and laymen that it is a media hype train.
I worked on ML projects before they got rebranded as AI. I get to sit in the room when these discussion happen with architects and actual leaders. This is Hype. Anyone who tells you other wise is lying or selling you something.
I see how that is a hype train, and I also work with machine learning (though I’m far from an expert), but I’m not convinced these things are not getting intelligent. I know what their problems are, but I’m not sure whether the human brain works the same way, just (yet) more effective.
That is, we have visual information, and some evolutionary BIOS, while LLMs have to read the whole internet and use a power plant to function - but what if our brains are just the same bullshit generators, we are just unaware of it?
I work in an extremely related field and spend my days embedded into ML/AI projects. I’ve seen teams make some cool stuff and I’ve seen teams make crapware with “AI” slapped on top. I guarantee you that you are wrong.
What if our brains…
There’s the thing- you can go look this information up. You don’t have to guess. This information is readily available to you.
LLMs work by agreeing with you and stringing together coherent text in patterns the recognize from huge samples. It’s not particularly impressive and is far, far closer to the initial chat bots from last century than they do real GAI or some sort of singularity. The limits we’re at now are physical. Look up how much electricity and water it takes just to do trivial queries. Progress has plateaued as it frequently does with tech like this. That’s okay, it’s still a neat development. The only big takeaway from LLMs is that agreeing with people makes them think you’re smart.
In fact, LLMs are a glorified Google at higher levels of engineering. When most of the stuff you need to do doesn’t have a million stack overflow articles to train on it’s going to be difficult to get an LLM to contribute in any significant way. I’d go so far to say it hasn’t introduced any tool I didn’t already have. It’s just mildly more convenient than some of them while the costs are low.
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.
