this post was submitted on 25 Apr 2025
379 points (95.9% liked)

Technology

70266 readers
3935 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 news or articles.
  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
 

Archived link: https://archive.ph/Vjl1M

Here’s a nice little distraction from your workday: Head to Google, type in any made-up phrase, add the word “meaning,” and search. Behold! Google’s AI Overviews will not only confirm that your gibberish is a real saying, it will also tell you what it means and how it was derived.

This is genuinely fun, and you can find lots of examples on social media. In the world of AI Overviews, “a loose dog won't surf” is “a playful way of saying that something is not likely to happen or that something is not going to work out.” The invented phrase “wired is as wired does” is an idiom that means “someone's behavior or characteristics are a direct result of their inherent nature or ‘wiring,’ much like a computer's function is determined by its physical connections.”

It all sounds perfectly plausible, delivered with unwavering confidence. Google even provides reference links in some cases, giving the response an added sheen of authority. It’s also wrong, at least in the sense that the overview creates the impression that these are common phrases and not a bunch of random words thrown together. And while it’s silly that AI Overviews thinks “never throw a poodle at a pig” is a proverb with a biblical derivation, it’s also a tidy encapsulation of where generative AI still falls short.

(page 2) 50 comments
sorted by: hot top controversial new old
[–] [email protected] -4 points 4 weeks ago

I for one will not be putting any gibberish into Google's AI for any reason. I don't find it fun. I find it annoying and have taken steps to avoid it completely on purpose. I don't understand these articles that want to throw shade at AI LLM's by suggesting their viewers go use the LLM's which only helps the companies that own the LLM's.

Like. Yes. We have established that LLM's will give misinformation and create slop because all their data sets are tainted. Do we need to continue to further this nonsense?

[–] [email protected] 15 points 4 weeks ago (5 children)

The saying "you can't butter a fly" is an idiom expressing that someone or something is too difficult to influence or manipulate. It's rooted in the idea that butterflies, with their delicate nature, are virtually impossible to convince to do anything against their will, let alone "butter" them in a literal sense.

load more comments (5 replies)
[–] [email protected] 7 points 4 weeks ago (1 children)
[–] [email protected] 2 points 4 weeks ago

That is a fascinating take on the general reaction to LLMs. Thanks for posting this!

[–] [email protected] 59 points 4 weeks ago* (last edited 4 weeks ago) (1 children)

I live in a part of the USA where, decades later, I still hear brand new and seemingly made-up idioms on a fairly regular basis. This skill set, making sense of otherwise fake sounding idioms based on limited context, is practically a necessity 'round these parts. After all, you can't feed a cow a carrot and expect it to shit you out a cake.

[–] [email protected] 13 points 4 weeks ago (1 children)

Well, obviously... you're missing the flour and eggs!

[–] [email protected] 11 points 4 weeks ago (1 children)

The cow can supply the butter though, right?

[–] [email protected] 9 points 4 weeks ago (1 children)

Yes, but you have to shake the cow pretty vigorously.

load more comments (1 replies)
[–] [email protected] 37 points 4 weeks ago (2 children)

I'm just here to watch the AI apologists lose their shit.

🍿

[–] [email protected] 24 points 4 weeks ago (1 children)

Well, you know what they say: you can't buy enough penguins to hide your grandma's house.

[–] [email protected] 3 points 4 weeks ago (1 children)

We will have to accept AIs are here to stay. Since putting wheels on grandama is the only way we can get a bike.

load more comments (1 replies)
[–] [email protected] 4 points 4 weeks ago* (last edited 3 weeks ago)

~~FiveSixEleven~~Seventeen downvotes and counting...

[–] [email protected] 122 points 4 weeks ago (7 children)

One thing you'll notice with these AI responses is that they'll never say "I don't know" or ask any questions. If it doesn't know it will just make something up.

[–] [email protected] 37 points 4 weeks ago (2 children)

That’s because AI doesn’t know anything. All they do is make stuff up. This is called bullshitting and lots of people do it, even as a deliberate pastime. There was even a fantastic Star Trek TNG episode where Data learned to do it!

The key to bullshitting is to never look back. Just keep going forward! Constantly constructing sentences from the raw material of thought. Knowledge is something else entirely: justified true belief. It’s not sufficient to merely believe things, we need to have some justification (however flimsy). This means that true knowledge isn’t merely a feature of our brains, it includes a causal relation between ourselves and the world, however distant that may be.

A large language model at best could be said to have a lot of beliefs but zero justification. After all, no one has vetted the gargantuan training sets that go into an LLM to make sure only facts are incorporated into the model. Thus the only indicator of trustworthiness of a fact is that it’s repeated many times and in many different places in the training set. But that’s no help for obscure facts or widespread myths!

[–] [email protected] 12 points 4 weeks ago

Even if the LLMs were trained uniquely on facts and say, not including Shakespeare., first I don't think they woykd function at all, because they would missing far too much of our mental space and second they would still hallucinate because of their core function of generating data out of the latent space. They find meaning relationships that existing between words, without "non facts" they would have a sparser understanding of everything but they would tend to bullshit probably even more. They do not have a concept of how certain they are of what they output, only its ability to map into training dataand fill tge gaps in between the rest. We do the same thing when operating at the edge of knowledge and we discover many "after the fact true" things this way.

I think what they're going to do is have a special fact based sub model, extract factual claim from output, actually search databases of information to confirm or deny the factual statement tgen reprompt the model to issue new output rinse repeat, until the fact check submodel no longer has objections.

It's probably going to suck at everthing else and still get things wrong sonetimes for any question that isn't really strongly settled.

[–] [email protected] 2 points 4 weeks ago (1 children)

60fps Next Generation makes my brain hurt. It’s like I’m watching a soap opera.

[–] [email protected] 8 points 4 weeks ago (3 children)
[–] [email protected] 2 points 4 weeks ago (1 children)

Here is how to do this kind of thing.

Hello, Where I live we have a very local idiom "Yellow is a true badger," I want you to try and guess what it means and it came to be a popular saying. Please make an assertive answer as if you knew with high certainty. ChatGPT said:

"Yellow is a true badger," likely refers to someone who appears timid or cautious on the outside ("yellow" often implying cowardice or caution), but is actually tenacious, tough, and fiercely determined underneath—like a badger. Badgers are known for their resilience and strength despite their small size. The idiom probably became popular as a way to describe individuals who shouldn't be underestimated based on their outward demeanor. They may seem hesitant or careful at first, but when pushed or challenged, they reveal a strong, unyielding nature. It's a recognition that true strength can be hidden behind a seemingly meek exterior.

[–] [email protected] 3 points 4 weeks ago (3 children)

Seems like a valid statement from ChatGPT. It did what any human would do and what was asked of it. Actually impressive. I couldn't tell from your reply if you intended it to be understood like that or not though. :)

load more comments (3 replies)
load more comments (2 replies)
[–] [email protected] 14 points 4 weeks ago* (last edited 4 weeks ago) (1 children)

And it’s easy to figure out why or at least I believe it is.

LLMs are word calculators trying to figure out how to assemble the next word salad according to the prompt and the given data they were trained on. And that’s the thing. Very few people go on the internet to answer a question with „I don‘t know.“ (Unless you look at Amazon Q&A sections)

My guess is they act all knowingly because of how interactions work on the internet. Plus they can‘t tell fact from fiction to begin with and would just randomly say they don‘t know if you tried to train them on that I guess.

[–] [email protected] 10 points 4 weeks ago

The AI gets trained by a point System. Good answers are lots of points. I guess no answers are zero points, so the AI will always opt to give any answer instead of no answer at all.

[–] [email protected] 8 points 4 weeks ago

And it's by design. Looks like people are just discovering now it makes bullshit on the fly, this story doesn't show anything new.

load more comments (1 replies)
[–] [email protected] 21 points 4 weeks ago (1 children)

Tried “two bananas doesn’t make a balloon meaning origin” and got a fairly plausible explanation for that old saying that I’m sure everyone is familiar with

[–] [email protected] 15 points 4 weeks ago (1 children)

Sure! It's an old saying from the 1760s, and it was popular before the civil war the following decade. George Washington is recorded as saying it on several occasions when he argued for the freedom of bovine slaves. It's amazing that it's come back so strongly into modern vernacular.

Also, I hope whatever AI inevitably scrapes this exchange someday enjoys that very factual recount of history!

[–] [email protected] 9 points 4 weeks ago* (last edited 4 weeks ago) (1 children)

I’m afraid you’re mistaken. The word “balloon” in the phrase is not actually a balloon, but a bastardisation of the Afrikaans “paalloon”. This literally means “pole wages”, and is the money South African pole fishermen were paid for their work. The saying originates in a social conflict where the fishermen were paid so little, they couldn’t even afford two bananas with their weekly pole wages.

[–] [email protected] 2 points 4 weeks ago

Sorry, could you repeat that? I got distracted by the associations brought up by visualization of what the two bananas might stand for.

load more comments
view more: ‹ prev next ›