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.
this post was submitted on 25 Apr 2025
2 points (100.0% liked)
Technology
85703 readers
4524 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related news or articles.
- Be excellent to each other!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- 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.
- Check for duplicates before posting, duplicates may be removed
- Accounts 7 days and younger will have their posts automatically removed.
Approved Bots
founded 3 years ago
MODERATORS
Well, obviously... you're missing the flour and eggs!
The cow can supply the butter though, right?
Yes, but you have to shake the cow pretty vigorously.
Just put on some moosic.
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.
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.
As an Autist, I find it amazing that... after a lifetime of being compared to a robot, an android, a computer...
When humanity actually does manage to get around to creating """AI"""... the AI fundamentally acts nothing like the general stereotype of fictional AIs, as similar to how an Autistic mind tends to evaluate information...
No, no, instead, it acts like an Allistic, Neurotypical person, who just confidently asserts and assumes things that it basically pulls out of its ass, often never takes any time to consider its own limitations as it pertains to correctly assessing context, domain specific meanings, more gramatically complex and ambiguous phrases ... essentially never asks for clarifications, never seeks out addtional relevant information to give an actually useful and functional reply to an overly broad or vague question...
Nope, just barrels forward assuming its subjective interpretation of what you've said is the only objectively correct one, spouts out pithy nonsense... and then if you actually progress further and attempt to clarify what you actually meant, or ask it questions about itself and its own previous statements... it will gaslight the fuck out of you, even though its own contradictory / overconfident / unqualified hyperbolic statements are plainly evident, in text.
... Because it legitimately is not even aware that it is making subjective assumptions all over the place, all the time.
Anyway...
Back to 'Autistic Mode' for Mr. sp3ctr4l.
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!
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.
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.
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. :)
Yes
You clearly haven't experimented with AI much. If you ask most models a question that doesn't have an answer, they will respond that they don't know the answer, before giving very reasonable hypotheses. This has been the case for well over a year.
You clearly haven't experimented with AI much in a work environment. When asked to do specific things that you are not sure if are possible it will 100% ignore part of your input and always give you a positive response at first.
"How can I automate outlook 2020 to do X?"
'You do XYZ'
me, after looking it up"that's only possible in older versions"
'You are totally right, you do IJK'
"that doesn't achieve what i asked"
'Correct, you can't do it.'
And don't get me started on APIs of actual frameworks... I've wished to punch it hard when dealing with react or spark. Luckily I usually know my stuff and only use it to find a quick example of something that I test locally before implementing if 5 mins of googling didn't give me the baseline, but the amount of colleagues that not only blindly copy code but argue with my reasoning saying "chatgpt says so" is fucking crazy.
When chatgpt says something I know is incorrect I ask for sources and there's fucking none. Because it not possible my dude.
'Correct, you can't do it.'
And this is the best case scenario. Most of the time it will be:
- How can I do [something]?
- Here are the steps: X, Y, Z
- No it doesn't work, because ...
- You're correct, it doesn't work! 🤗 Instead you should do A, B, C to achieve [something else]
- That's not what I asked, I need to do [something]
- Here are the steps: X, Y, Z
- Listen here you little...
Useless shit you can't trust.
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.
The premium version has gotten a LOT better in recent months. I just fed it,
"you can't soothe a tree" meaning
And it replied with: This phrase is not a standard idiom with a widely recognized meaning. Its interpretation depends on the context in which it is used. Literally, it means you cannot comfort or calm a tree in the way you would a sentient being, as trees do not possess emotions or consciousness that can be "soothed". Metaphorically, it likely means:
- Some entities (problems, situations, perhaps even certain people) are unresponsive to attempts at emotional comfort or calming.
- Trying to apply emotional solutions or appeals to things that are inherently non-emotional or unchangeable is futile.
- It could describe someone who is extremely stoic, impassive, or emotionally unavailable. The specific meaning depends heavily on the situation where the phrase was encountered.
I always wonder how many of these are actually just patches behind the scene to fix viral trends. Or even more devious, they use the viral trends to patch a specific failure point to make it feel like progress is being made.
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.
This is a great example - it kinda makes sense if you skim read it but butterflies have nothing to do with butter, just like hotdogs have nothing to do with dogs.
No, that phrase means "this situation is hopeless because the person is incapable of change". You can't turn a fly into a butterfly, no matter how hard you try.
"three horses, one carrot, a slice at a time or live in purple sauce"
When many want the same reward, it must be shared slowly—or chaos/absurdity ensues.
I'm just here to watch the AI apologists lose their shit.
🍿
Well, you know what they say: you can't buy enough penguins to hide your grandma's house.
We will have to accept AIs are here to stay. Since putting wheels on grandama is the only way we can get a bike.
I am not saying other generative AI lack flaws, but Google's AI Overview is the most problematic generative AI implementation I have ever seen. It offends me that a company I used to trust continues to force this lie generator as a top result for the #1 search engine. And to what end? Just to have a misinformed populace over literally every subject!
OpenAI has issues as well, but ChatGPT is a much, much better search engine with far fewer hallucinations per answer. Releasing AI Overview while the competition is leagues ahead on the same front is asinine!
They famously taught it on Reddit. So it's not surprising that it just comes up with nonsense.
You would have thought that they would use a more stable data set. Although it does mean it's very good at explaining the plots of movies badly.
You may not even be able to lick a badger once, if it's already angry. Which it will be because it's a fuckin' badger.
"No man ever licks the same badger twice" - Heroclitus
This is both hysterical and terrifying. Congratulations.
http://www.newforestexplorersguide.co.uk/wildlife/mammals/badgers/grooming.html
Mutual grooming between a mixture of adults and cubs serves the same function, but additionally is surely a sign of affection that strengthens the bond between the animals.
A variety of grooming postures are adopted by badgers but to onlookers, the one that is most likely to raise a smile involves the badger sitting or lying back on its haunches and, with seemingly not a care in the world (and with all hints of modesty forgotten), enjoying prolonged scratches and nibbles at its under-parts and nether regions.
That being said, that's the European badger. Apparently the American badger isn't very social:
https://a-z-animals.com/animals/comparison/american-badger-vs-european-badger-differences/
American badger: Nocturnal unless in remote areas; powerful digger and generally more solitary than other species. Frequently hunts with coyotes.
European badger: Digs complicated dens and burrows with their familial group; one of the most social badger species. Depending on location, hibernation may occur.
This feels like a good metaphor for US vs EU culture.
Try this on your friends, make up an idiom, then walk up to them, say it without context, and then say "meaning?" and see how they respond.
Pretty sure most of mine will just make up a bullshit response nd go along with what I'm saying unless I give them more context.
There are genuinely interesting limitations to LLMs and the newer reasoning models, and I find it interesting to see what we can learn from them, this is just ham fisted robo gotcha journalism.
My friends would probably say something like "I've never heard that one, but I guess it means something like ..."
The problem is, these LLMs don't give any indication when they're making stuff up versus when repeating an incontrovertible truth. Lots of people don't understand the limitations of things like Google's AI summary* so they will trust these false answers. Harmless here, but often not.
* I'm not counting the little disclaimer because we've been taught to ignore smallprint from being faced with so much of it
My friends would probably say something like "I've never heard that one, but I guess it means something like ..."
Ok, but the point is that lots of people would just say something and then figure out if it's right later.
The problem is, these LLMs don't give any indication when they're making stuff up versus when repeating an incontrovertible truth. Lots of people don't understand the limitations of things like Google's AI summary* so they will trust these false answers. Harmless here, but often not.
Quite frankly, you sound like middle school teachers being hysterical about Wikipedia being wrong sometimes.
LLMs are already being used for policy making, business decisions, software creation and the like. The issue is bigger than summarisers, and "hallucinations" are a real problem when they lead to real decisions and real consequences.
If you can't imagine why this is bad, maybe read some Kafka or watch some Black Mirror.
This also works with asking it "why?" About random facts you make up.