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.
This also works with asking it “why?” About random facts you make up.
“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.
“AI cannot peel the cat down to the dog’s bark”
AI can’t reduce complex, chaotic, or nuanced things (like a cat) into something simple or binary (like a dog’s bark).
A binary dog will never pee you virtual bananas.
A purely logical or programmed entity (like AI) will never give you true absurdity, spontaneity, or joyfully irrational experiences (the “virtual bananas”).
“The one who lives thinking of fruit in Uranus will never eat a banana.”
If you’re too obsessed with absurd or far-off ideas, you’ll miss what’s right in front of you.
“A vaccine with no green paint will never straighten its leaves.”
solution that lacks vitality or authenticity can’t truly heal or nurture life. Or, you can’t fix organic problems with lifeless tools.
I mean are you asking it if there is a history of an idiom existing or just what the idiom could mean?
3 ways to skin a horse
What? Why is that?
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 cross over a duck’s river” is a play on words, suggesting that it’s difficult to cross a river that is already filled with ducks. It’s not a literal statement about rivers and ducks, but rather an idiom or idiom-like phrase used to express the idea that something is difficult or impossible to achieve due to the presence of obstacles or challenges.
I used the word “origin” instead of “meaning”, which didn’t seem to work.
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.
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.
60fps Next Generation makes my brain hurt. It’s like I’m watching a soap opera.
Sounds like a lot of people I know.
It was trained in the internet. Everybody else is wrong there.
Do you listen to those people or ask them question about things you want to learn more about?
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.
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.
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.
Your search - “yellow is a true badger” meaning - did not match any documents.
Suggestions:
Make sure that all words are spelled correctly. Try different keywords. Try more general keywords. Try fewer keywords.
definition of saying yellow is a true badger
The saying “yellow is a true badger” is not a standard or recognized idiom. The phrase “that’s the badger” (or similar variations) is a British idiom meaning “that’s exactly what I was looking for” or “that’s the right thing”. The term “yellow” is often used to describe someone who is cowardly. Therefore, there’s no established meaning or relationship between “yellow” and “true badger” in the way the phrase “that’s the badger” is used.
still didn’t work.
That was my point. In think you are reading two comments into one.
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
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.
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.
I’d prefer if I didn’t have to iterate twice…
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!
Its a language model not a dictionary. By putting the term “definition” before the sentence you imply that the following sentence has a definintion, hence it vectors down to the most likely meaning.
Buddy, I never said the word definition
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.
And to what end? Just to have a misinformed populace over literally every subject!
This is a feature; not a bug. We’re entering a new dark age, and generative AI is the tool that will usher it in. The only “problem” generative AI is efficiently solving is a populace with too much access to direct and accurate information. We’re watching as perfectly functional tools and services are being rapidly replaced by a something with inherent issues with reliability, ethics and accountability.
In the case with Google AI overview, I 1000% agree. I am not against all AI tools, but that company has clearly chosen evil.
I’ve resorted to appending every Google search with “-ai” because I don’t want to see their bullshit summaries. Outsourcing our thinking is lazy and dangerous, especially when the technology is so flawed.
I like that trick, noted! I mostly use DuckDuckGo as a browser and search engine now. If it fails I use ChatGPT
Saying you used to trust google is really a core part of the problem. Google isn’t a person. Just like AI isn’t a person. They both do what they are tasked with. Companies prioritize profit. AI prioritizes giving an answer, not necessarily a correct one. That is how it was designed.
Impressive how we seem to agree with each other yet you still found a way to insult my way of putting it
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.
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.
FiveSixEleven downvotes and counting…
That is a fascinating take on the general reaction to LLMs. Thanks for posting this!
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
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!
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.
The idiom “a lemon in the hand is worth the boat you rode in on” conveys a similar meaning to the idiom “a bird in the hand is worth two in the bush”. It emphasizes that it’s better to appreciate what you have and avoid unnecessary risks or changes, as a loss of a current advantage may not be compensated by a potential future gain. The “lemon” represents something undesirable or less valuable, but the “boat” represents something that could potentially be better but is not guaranteed.
The saying “better a donkey than an ass” plays on the dual meaning of the word “ass.” It suggests that being called a donkey is less offensive than being called an ass, which can be used as an insult meaning stupid or foolish. The phrase highlights the contrast between the animal donkey, often seen as a hardworking and steady companion, and the derogatory use of “ass” in everyday language.
Yep, it does work
Better a pineapple thananananas…
I think that’s a great phrase!
Didn’t work for me. A lot of these ‘gotcha’ AI moments seem to only work for a small percentage of users, before being noticed and fixed. Not including the more frequent examples that are just outright lies, but get upvoted anyway because ‘AI bad’
It looks like incognito and adding “meaning AI” really gets it to work just about every time for me
However, “the lost dog can’t lay shingles meaning” didn’t work with or without “AI”, and “the lost dog can’t lay tiles meaning” only worked when adding “AI” to the end
So it’s a gamble on how gibberish you can make it I guess
I found that trying “some-nonsense-phrase meaning” won’t always trigger the idiom interpretation, but you can often change it to something more saying-like.
I also found that trying in incognito mode had better results, so perhaps it’s also affected by your settings. Maybe it’s regional as well, or based on your search result. And, as AI’s non-deterministic, you can’t expect it to always work.
Now I’ll never know what people mean when they say “those cupcakes won’t fill a sauna”!
