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.
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.
only boomers and tech-unsavy people think that.
Next you’ll tell me half the population has below average intelligence.
Not really endorsing LLMs, but some people…
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.
“US”… Even LLM won’t vote for Trump
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?
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.
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.
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!
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…”
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
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.
Half of all voters voted for Trump. So an LLM might be smarter than them. Even a bag of pea gravel might be.
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.
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
A bag of frozen peas’s is smarter than some of these Trump followers. Even half a frozen pea is.
