this post was submitted on 17 Mar 2025
534 points (96.8% liked)

Technology

66783 readers
4781 users here now

This is a most excellent place for technology news and articles.


Our Rules


  1. Follow the lemmy.world rules.
  2. Only tech related content.
  3. Be excellent to each other!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
  9. Check for duplicates before posting, duplicates may be removed
  10. Accounts 7 days and younger will have their posts automatically removed.

Approved Bots


founded 2 years ago
MODERATORS
 

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.
top 50 comments
sorted by: hot top controversial new old
[–] [email protected] 5 points 1 hour ago

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.

[–] [email protected] 5 points 1 hour ago (1 children)

oh my god 49% of LLM users are pathologically stupid.

and still wrong.

[–] [email protected] 4 points 1 hour ago (1 children)

Still better than reddit users...

[–] [email protected] 3 points 1 hour ago

where do you think these idiots spend their time?

[–] [email protected] 7 points 2 hours ago (1 children)

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.

[–] [email protected] 2 points 1 hour ago (1 children)

literally dogs are smarter and have more reasoning ability.

[–] [email protected] 1 points 52 minutes ago (1 children)

Than half of LLM users? Probably

[–] [email protected] 1 points 49 minutes ago

also that, yes.

[–] [email protected] 1 points 1 hour ago* (last edited 1 hour ago) (1 children)

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.

[–] [email protected] 1 points 25 minutes ago

The statement is "smarter", not "possesses more information". None of the things you listed (LLMs, libraries, Wikipedia, etc.) have any capacity to reason.

[–] [email protected] 0 points 41 minutes ago
[–] [email protected] 1 points 2 hours ago (1 children)

only boomers and tech-unsavy people think that.

[–] [email protected] 1 points 1 hour ago

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.

[–] [email protected] 19 points 5 hours ago (1 children)

Next you'll tell me half the population has below average intelligence.

Not really endorsing LLMs, but some people...

[–] [email protected] 1 points 1 hour ago

pathologically stupid, and still wrong. yes.

[–] [email protected] 5 points 5 hours ago

"US".... Even LLM won't vote for Trump

[–] [email protected] 26 points 9 hours ago (1 children)

moron opens encyclopedia "Wow, this book is smart."

[–] [email protected] 7 points 6 hours ago

If it's so smart, why is it just laying around on a bookshelf and not working a job to pay rent?

[–] [email protected] 11 points 8 hours ago (1 children)

i guess the 90% marketing (re: linus torvalds) is working

[–] [email protected] 3 points 6 hours ago

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.

[–] [email protected] 18 points 9 hours ago (2 children)

If you don't have a good idea of how LLM's work, then they'll seem smart.

[–] [email protected] 1 points 1 hour ago

Until you ask them how many R's are in strawberry.

[–] [email protected] 8 points 8 hours ago* (last edited 8 hours ago) (6 children)

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.

[–] [email protected] 1 points 3 hours ago* (last edited 3 hours ago)

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.

load more comments (5 replies)
[–] [email protected] 13 points 9 hours ago (1 children)

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.

[–] [email protected] 11 points 8 hours ago (1 children)

So LLMs are confident you say. Like a very confident man. A confidence man. A conman.

[–] [email protected] 3 points 6 hours ago

You know, that very sequence of words entered my mind while typing that comment!

[–] [email protected] 43 points 12 hours ago (8 children)

And you know what? The people who believe that are right.

Note that that’s not a commentary on the capabilities of LLMs.

[–] [email protected] 1 points 1 hour ago* (last edited 1 hour ago)

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.

load more comments (7 replies)
load more comments
view more: next ›