- 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.
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.
oh my god 49% of LLM users are pathologically stupid.
and still wrong.
Still better than reddit users…
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.
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.
“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.
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…”
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.
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.
A bag of frozen peas’s is smarter than some of these Trump followers. Even half a frozen pea is.
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.
if by months away, you mean months ago, then yeah
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
Given the US adults I see on the internet, I would hazard a guess that they’re right.
