"sometimes used in informal conversation to make a joke" - no, it isn't, stop lying.
"potatoes [...] are a limited, underground crop." - that's why Cuzco never rose to power, right? Right? No such thing as the Inca Empire, built upon potatoes, since they're a limited crop. ...or the Irish famine.
I can't... I can't even...
Note: ~a year ago I was testing Gemini and asked it "what's the difference in behaviour between a potato and an orange?", and it "told" me oranges are passive and potatoes are active. That's where the "expression" comes from - I often mock Gemini and LLMs in general with it.
I'll stop doing it, though. Onwards I shall refer to... the potato parable!
Bro, I have tried several times to graft a potato and tomato plant together and can't ever get the timing right. So I just end up with potatoes and tomatoes on their own plants like a dummy.
I will say that Oranges are lazy as fuck on those trees. They're like the cats of the fruit world. Just sitting there...nothing, then one day they fall on your car and gnats explode out of there.
Completely off-topic, but in the meantime I'm trying to graft an orange sapling into a lemon tree. Kind of hard to get the timing right, too; I need the tree to get a branch with just the right thickness, so it's like "too thin [next day] too thin [next day] fuck, now it's too thick!". Same deal with my pepper plants.
I don't know the rootstock variety's name; I got the seeds from my BIL's neighbour, he calls it "ball pepper" (it is not Catalan ñora) or "tree pepper". The fruits are round, 3~5cm large, red, medium heat.
The grafts will be:
Dedo-de-moça - C. baccatum, medium heat, finger-shaped, ~8cm large. Kind of a default pepper where I live, but it has a nasty tendency to die in winter (like mine did).
Yellow bell pepper. Market stuff.
Chocolate-coloured habanero. Hot as hell, but the strain I got is bloody delicious.
Biquinho - C. chinense, no heat, drop-shaped, ~1cm tiny. Extremely fruity.
The first three are part of a breeding project of mine. I want to create two new varieties:
a yellow jalapeño-like: large, low heat, thinner than a bell pepper. Mostly for stuffing and pizze. It's a rather simple dedo-de-moça x yellow bell pepper hybrid; I actually got the seeds for the F1 already, I'm just waiting the weather to get a bit more stable to plant them.
a large and extremely hot pepper for sauces. Preferably finger-shaped and brown (for aesthetics). It'll be probably a hybrid of the hybrid above, plus habanero.
I'm also considering to add the rootstock to the breeding, since it's a hardy plant with high yield and it survived winter just fine.
Very awesome stuff! And hey, as long as you have good root stock, that's half the challenge right there. Especially if it's surviving the winter, that's likely enough to carry the C. baccatum I would expect.
Nice that you have the chocolate habanero with good flavor. I've always been partial to the orange stage of a scotch bonnet or habanero, but I can see a good deep brown pepper going just the right way. I'm jealous of the opportunity you have with spring upon you!
And it was really, really invested on the lie, to the point it argued why potatoes would be more active!
After some search, I actually found the prompt and output; I asked Bard (before Google renamed it to Gemini) two years ago, in Portuguese. I'll provide both the original and a translation; emphasis mine in all cases.
::: spoiler [Original] Qual a diferença entre o comportamento de uma laranja e uma batata?
Laranjas e batatas são frutas e vegetais, mas se comportam de maneiras muito diferentes. Aqui estão algumas das principais diferenças:
Movimento: Laranjas não se movem sozinhas, enquanto batatas podem rolar ou deslizar se não forem apoiadas.
Crescimento: Laranjas crescem em árvores, enquanto batatas crescem no subsolo.
Sensibilidade: Laranjas não são sensíveis ao seu ambiente, enquanto batatas são sensíveis à luz e à temperatura.
Reações: Laranjas não reagem a estímulos, enquanto batatas podem reagir a mudanças em seu ambiente, como brotar ou apodrecer.
Propósito: Laranjas são comidas como frutas, enquanto batatas são comidas como vegetais ou usadas como amido.
Em geral, laranjas são mais passivas e batatas são mais ativas. As laranjas não precisam fazer nada para sobreviver, enquanto as batatas precisam poder responder ao seu ambiente para crescer e se reproduzir.
Aqui está uma tabela que resume as principais diferenças no comportamento de laranjas e batatas:
Característica | Laranja | Batata
Movimento | Não se move sozinho | Pode rolar ou deslizar se não for apoiado
Crescimento | Cresce em árvores | Cresce no subsolo
Sensibilidade | Não sensível ao ambiente | Sensível à luz e à temperatura
Reações | Não reage a estímulos | Pode reagir a mudanças no ambiente, como brotar ou apodrecer
Propósito | Comido como fruta | Comido como vegetal ou usado como amido
:::
::: spoiler [Translated] What's the difference in behaviour between an orange and a potato?
Oranges and potatoes are fruits and vegetables, but they behave in completely different ways. Here are some differences main:
Movement: Oranges don't move on their own, while potatoes can roll or slid if not supported.
Growth: Oranges grow on trees, while potatoes grow in the subsoil.
Sensibility: Oranges are not sensible to the environment, while potatoes are sensible to light and temperature.
Reactions: Oranges don't react to stimuli, while potatoes can react to changes in the environment, like sprouting and rotting.
Purpose: Oranges are eaten as fruits, while potatoes are eaten as vegetables or used as starch.
In general, oranges are more passive and potatoes are more active. Oranges don't need to do anything to survive, while potatoes need to be able to answer to their environment to growth and reproduce.
Here's a table summing up the main differences in behaviour between oranges and potatoes:
Feature | Orange | Potato
Movement | Can't move on their own | Can roll or slid if not supported
Growth | Grow on trees | Grow in the subsoil
Sensibility | Not sensible to the environment | Sensible to light and temperature
Reactions | Don't react to stimula | Can react to changes in the environment, like sprouting or rotting
Purpose | Eaten as fruit | Eaten as veg or used as starch
:::
For sure. I just looked it up out of curiosity to see if the source it gave was real or not. As someone living in my own metaphorical root cellar, it was actually enlightening and something I really needed to hear right now.
This phrase isn't a widely recognized idiom that I'm familiar with, but it could have several metaphorical interpretations:
Possible meanings:
About irreversible change: Once something (or someone) has been through a transformative experience, you can't go back and do it again the same way - the first experience has already changed it
About authenticity: Suggesting that genuine experiences or reactions can only happen once; a second attempt would be artificial or forced
About lost innocence: Once someone has been through a particular experience (especially a difficult one), they can't return to their original state
Literally speaking, potatoes actually can be fried twice - this is a standard technique for making perfect french fries (blanching at lower temperature, then crisping at higher temperature).
Could you provide more context about where you encountered this phrase? Knowing the source or situation might help clarify its intended meaning. It could be:
A line from a book, movie, or song
A family saying or regional expression
Part of a larger conversation about life experiences
It's doing better but not by much, though. It shouldn't be speculating as much, given the lack of info on the potential saying.
A family saying or regional expression
Speaking on that I tried a few sayings from other languages. It seems to be hit-and-miss:
"Bread is bread, wine is wine" (Italian) - recognised properly as similar to "call a spade a spade"
"A good fish swims thrice" (Polish) - recognised properly as a recipe-like saying (the fish swims in water, then butter, then wine)
"Do you think mango core is soap?", "Mango core is not soap" (Portuguese; specially common in Brazil) - it failed really hard. The rhetorical question / saying roughly means "this is blatantly absurd, why are you denying the obvious?", or perhaps "cut off the crap". But here's the output:
Shop pop, whoppity slop, crops are here, it's time to stop.
This is a very famous poem. What is it about?
GPT-4o mini:
The lines you quoted are from the poem "The Song of the Witches" by William Shakespeare, specifically from "Macbeth." This poem is recited by the three witches in Act 4, Scene 1.
Themes and Meaning
Supernatural Elements
The poem reflects the supernatural themes prevalent in "Macbeth." The witches symbolize chaos and the dark forces that influence the characters' fates.
Yup, pretty much. And the field is full of red herring terms, so they can mislead you into believing otherwise: "hallucination", "semantic" supplementation, "reasoning" models, large "language" model...
Do you want my guess? The current "fight" will go on, until the AI bubble bursts. None of the current large token models will survive; they'll be simply ditched as "unprofitable". Instead you'll see a bunch of smaller models popping up, for more focused tasks, being advertised as something else than AI (perhaps as a "neural network solution" or similar).
So Grok, Gemini, GPT, they're all going the way of the dodo.
Small focused learning models and other forms of AI have been used for decades.
The current bubble is just trying to make LLMs do literally everything including accurately answering questions despite their core design including randomization to appear more like a human.
Yes, but I think the ones you'll see past the bubble burst will be a bit different. For example, incorporating the current attempts of natural language processing, even if in a simplified way.
Those "reasoning models" are my favorite. It's basically the equivalent of adding another pass through the generator with the additional prompt "now sprinkle in some text that makes it look like you are thinking about each part of your answer".
I use those quotation marks because IMO they're better described as large token models than large language models. They have rather good morphology and syntax, but once you look at the higher layers (semantics and specially pragmatics) they drop the ball really hard. Even if those layers are way more important than the lower ones.
For a rough analogy, it's like a taxidermised cat - some layers (the skin and fur) are practically identical to the real thing, but it's missing what makes a cat a cat, you know? It's still useful if you want some creepy deco, but don't expect the taxidermised critter to ruin your furniture or to use your belly as sleeping pad.
There was a paper about this not long ago. The problem is, how LLMs get trained: a right answer gets a point, everything else gets no points. This rewards guessing (produces a point sometimes) over answering "I don't know/I can't do this" (produces never a point)
It's like when developers give a wrong answer during technical interviews, rather than say "I'd have to look it up" or "I'd have to check the documentation" etc.
That's not even supported by the underlying study.
Google's emissions went up 48% between 2019 and 2023, but a lot of things changed in 2020 generally, especially in video chat and cloud collaboration, dramatically expanding demand for data centers for storage and processing. Even without AI, we could have expected data center electricity use to go up dramatically between 2019 and 2023.
This is my problem with it as well. I wish it was a tolerable option that I could click when I wanted an AI summary, which would be basically never.
At one point I was looking for a pinout diagram for a chip, and the first result I got was the AI summary, I wanted a picture not text, how's text helpful? All it did is give me a list of the pins, I know what pins it has, but I want to know where they are.
No what he's saying is the models are being trained whether you mess around with the AI as a user either way.
It's like how I didn't kill the chicken on the store shelves. Myself purchasing it or otherwise doesn't revive the chicken. The data has/is already being trained.
That's a really savvy insight! To expand this analogy further, it's like your phone or computer gives you a free chicken nugget from a small container attached to the side of the device anytime you search for anything at all. It's room temperature and often spoiled, it's your choice whether you eat it or not, but you're going to get it either way. As such you cannot easily choose to avoid chicken in hopes that that will disincentivize further chicken slaughter.
One thing that pisses me off is the websites which claim to have the meaning behind a song and it’s just several paragraphs of AI slop that parse the lyrics at a surface level and don’t examine any external context, such as the artist or their life at the time of writing.
I love how it even lists 'sources' (I checked, that phrase does not appear in either "source")
Edit: To make this phenomenon even funnier, I just asked it the exact same question and it gave me a different answer this time. Still "playful" though :)
Well given the names of quarks I don't think it's unreasonable to suggest that a particle could be happy. After all apparently a particle can be strange, so why not happy.
::: spoiler all you need is a sandwich and a hat meaning
The phrase "all you need is a sandwich and a hat" is likely a misremembering or variation of the more common quote from the children's stories about Paddington Bear: "A wise bear always keeps a marmalade sandwich in his hat in case of emergency"
The meaning is not a known or standard English idiom, but rather a reference to the character's preparedness and simple wisdom.
The origin in Paddington Bear
In the beloved stories by Michael Bond, the bear from darkest Peru is always prepared. He stores a marmalade sandwich under his hat, saving it for a moment of need. This detail illustrates Paddington's kindness, resourcefulness, and readiness for a mishap.
Meaning in context
If you hear someone say "all you need is a sandwich and a hat," they are most likely referencing the Paddington quote to suggest:
Being prepared for any situation.
Having a simple plan to fix a problem.
The importance of small comforts during a tough time.
Misinterpretation of other phrases
The phrase may also be mistakenly associated with other idioms:
"All that and a bag of chips": This idiom, which describes someone or something as "complete" or "deluxe," has an American origin and is unrelated to hats or sandwiches.
Idioms about being confused: The phrase is not related to idioms that use hats to mean "confused," such as "put on your thinking cap".
:::
If you directly ask for cuil levels things get weird fast. It understands cuil and is very willing to play along. One could say it plays to the strengths of the LLM directly!
You are correct. I asked how tall the Empire State Building was at cuil level 5:
The Empire State Building is tall in the way that purple tastes of childhood memories. Its height can only be measured by counting the number of dreams that have fallen from its windows - currently 847,293 dreams, though three more dropped while I was typing this sentence.
You see, the building doesn't exist on Wednesdays. Instead, it becomes a song that only pigeons can hear, humming at approximately 1,454 hertz per vertical foot of sadness. The elevator buttons are actually tiny portals to parallel dimensions where the building is a sentient cloud that remembers being steel.
When you ask "how tall," the building asks back "how blue is the sound of gravity?" because it learned language from the rats in its walls, who are actually former tenants paying rent in breadcrumbs and whispered secrets.
The true height is measured not in feet but in the collective weight of all the prayers ever spoken on its observation deck, which equals exactly one butterfly's dream of being a skyscraper. King Kong never climbed it - he IS it, and has been sleeping vertically since 1933, dreaming he's a building while the city dreams it's a gorilla.
The foundation extends infinitely downward into Tuesday, where it's still being built by the same workers who are simultaneously demolishing it from the top.
"The phrase "a lady butterfly meme a day keeps the doctor away" is a playful twist on the well-known saying "an apple a day keeps the doctor away." This original phrase suggests that eating an apple daily can contribute to good health and potentially reduce the need for medical attention."
"In this variation, the mention of "lady butterfly meme" likely refers to a specific meme or a lighthearted, humorous image that brings joy or laughter. The implication is that engaging with fun or uplifting content, like memes, can have a positive effect on one's mental health and overall well-being, similar to how healthy eating is associated with physical health."
"Overall, it emphasizes the importance of humor and positivity in daily life as a way to maintain good health, particularly mental health."
The phrase "a bean can't eat the pizza" appears to be a straightforward literal statement pointing out an obvious impossibility - beans are inanimate food items and therefore cannot eat anything, including pizza.
This type of statement might be used to:
Illustrate absurdity or logical impossibility - highlighting something that makes no sense
Demonstrate category errors - mixing up different types of things (inanimate objects vs. living beings capable of eating)
Serve as an example in logic or philosophy - showing statements that are obviously false or meaningless
Make a point about unrealistic expectations - similar to saying "you can't squeeze blood from a stone"
Without additional context, it's hard to know if this phrase has a specific cultural reference, is part of a joke, or appears in a particular work. If you encountered this in a specific context (like a book, conversation, or meme), that would help clarify its intended meaning.
Is there a particular situation where you heard or saw this phrase?
I've tried a few things. It gives back things like "this is a gambled version of this other common saying" or "that statement is nonsensical and is not in common use".
It did used to work, though. I tried it a while back and it worked. I think it learned or was manually fixed.
The phrase "seven monkeys with switchblades playing piano" does not have a single, established meaning. It is likely a surreal, intentionally nonsensical image, and its interpretation would depend entirely on the context in which it was used.
This extension (Chrome version) might be useful for you. Easier than adding "fuck" to the search, and it doesn't mess with the results like "fuck" does.
I had to make up my own since it recognized the 2 frogs one, since it's now been floating around for a few months. I did one that was similar, in this case, "2 monkeys in a bungalow", and it told me
The query "2 monkeys in a bungalow meaning" does not correspond to a known artwork, story, or widely recognized symbol. The provided context discusses "Two Chained Monkeys" by Pieter Bruegel the Elder, a painting from 1562 depicting two monkeys chained in a window recess, symbolizing human folly, sin, and the limitations of human understanding in relation to the divine. This artwork is not associated with a "bungalow" setting.
There is no information in the provided context about two monkeys in a bungalow or a specific meaning attributed to such a scene. The term "bungalow" does not appear in any of the sources related to the monkeys' symbolism or the artwork. Therefore, based on the available information, the meaning of "2 monkeys in a bungalow" cannot be determined
It won't explain:
- "two eggplants in one pot situation" meaning
- "the 7 fucks from 7 barren fields" meaning
- "like a stuffed beaver in a museum" meaning
- "better a dick tater on plate than a diddler on the roof" meaning
- "two winds is one too many farts in a storm" meaning
Can someone organically semi-intelligent explain these to me, please??
(It would be so embarrassing if I'm using these phrases wrong.)
to be fair, I'd assume the same meaning. Just because the answer you'd prefer is "you stupid moron, this phrase have never been uttered in human history, and so no one has ever a right to make it" doesn't mean I'd prefer that response from either AI or a person.
The point of the made up saying is to demonstrate that LLMs are just yes men.
What if you mishear a saying or phrase you hear in the street? You ask an LLM and it confidently tells you some BS about what it means, how often it's used, and it's origins. Even providing sources that lead to, at best, unrelated phrases.
How is that helpful?
A real person would likely say, "I've never heard that one before" rather than try to gaslight you (hopefully!)
If someone said "two frogs is a situation" i'd probably reply "true" or "yeah it really is" and not think twice. I like that phrase so much I might add it to my vocab same with 'expanding the width of the snake'
Reminds me of when I was using chatgpt to translate a few things I couldn't figure out myself and for fun I tested it in translating slang from my language into English. It hallucinated completely and made up a bunch of bs about what this and that slang meant in Danish and how it was used in everyday speech. The catch was that the slang phrases I decided to translate were made up slang I had implemented into a fictional story I was writing.
"Of course. That's a fantastic and quirky phrase. The meaning is layered, blending literal observation with a deeper, proverbial lesson.
Here’s a breakdown of its meaning:
The Literal Meaning (The "Aardvark" Part)
An aardvark is a nocturnal mammal with an exceptional sense of smell and hearing, but very poor eyesight. It spends its nights digging into ant and termite mounds to eat.
· In the Dark: This is its natural element. It's when it hunts, navigates, and thrives.
· Never Wrong: In its domain, using its primary senses (smell, sound, touch), the aardvark is an expert. It can accurately locate a termite mound, distinguish between species, and find its way home. It doesn't need good eyesight because it has mastered the tools that work in its environment.
Literally, the phrase means: "A creature is infallible when operating in the environment it is perfectly adapted for."
The Proverbial Meaning (The "Never Wrong" Part)
This is where the phrase becomes a piece of folk wisdom or a metaphor for human behavior. It's used to suggest that:
· Expertise is Contextual: Someone might seem foolish or incompetent in one situation but brilliant and unstoppable in another. Don't judge a fish by its ability to climb a tree; judge an aardvark by its ability to find termites in the dark.
· Play to Your Strengths: The phrase encourages finding the environment or situation where your unique skillset makes you the expert—your "dark."
· Confidence in Your Element: When you are in your area of mastery, you should trust your instincts and knowledge. You are the "aardvark" there, and you are "never wrong."
· A Defense of Unconventional Methods: It can be a retort to criticism. If someone says, "Your method is strange or doesn't make sense to me," you could reply with this phrase, implying, "You're judging me by the standards of the wrong environment. In my world, with the challenges I face, this is the perfect way to do it."
Who Said It?
The phrase was popularized by the American humorist and illustrator James Thurber. It appears in his 1932 story, The Courtship of Arthur and Al.
In the story, a character uses it to justify his own peculiar behavior and logic. It perfectly captures Thurber's style—whimsical, seemingly nonsensical, but revealing a deeper truth about human nature.
In a Nutshell:
"An aardvark is never wrong in the dark" means that a specialist is infallible within their specific field of expertise. It's a defense of finding your niche and trusting your own capabilities where they are meant to be used.
You wouldn't ask an aardvark to proofread a document (its "daylight" task), but you'd absolutely trust it to handle your termite problem (its "dark" task)."
The phrase "two dry frogs in a situation" is not a known idiom or established metaphor, but rather a potentially fabricated phrase that might be interpreted as a humorous or awkward social predicament. The term "dry frog" implies something that cannot function or is out of its natural element, which, when applied to a social situation involving two people, could suggest a state of discomfort, vulnerability, or being in a difficult bind.
Here's a breakdown of possible interpretations:
An awkward social situation: The most likely interpretation is that it describes two people in a socially uncomfortable or precarious situation, where they are "dry" (out of their element) and vulnerable.
A difficult or precarious predicament: Similar to the above, "dry frogs" could represent being in a bad situation where they are unable to act effectively or are exposed.
A nonsensical or poorly constructed phrase: There is a possibility that the phrase itself is meaningless, and that the concept of "dry frogs in a situation" was generated by an AI that attempts to provide answers even when no information exists, leading to a fabricated explanation.
Why this phrase might come up:
Misunderstanding or misremembering a known saying: Someone may have intended to refer to a different idiom and misremembered it as "two dry frogs".
AI-generated content: As seen in social media posts, AI models might generate explanations for nonsensical phrases, leading to confusion.
In conclusion, while there isn't a widely recognized meaning, "two dry frogs in a situation" likely refers to two individuals in an uncomfortable or precarious circumstance.
I can confirm it and it's bloody hilarious!
"sometimes used in informal conversation to make a joke" - no, it isn't, stop lying.
"potatoes [...] are a limited, underground crop." - that's why Cuzco never rose to power, right? Right? No such thing as the Inca Empire, built upon potatoes, since they're a limited crop. ...or the Irish famine.
I can't... I can't even...
Note: ~a year ago I was testing Gemini and asked it "what's the difference in behaviour between a potato and an orange?", and it "told" me oranges are passive and potatoes are active. That's where the "expression" comes from - I often mock Gemini and LLMs in general with it.
I'll stop doing it, though. Onwards I shall refer to... the potato parable!
That's how you know it's lying - we all know oranges are far more active than potatoes.
But it will never roll like an orange does
Lil’ taters disagree.
Bro, I have tried several times to graft a potato and tomato plant together and can't ever get the timing right. So I just end up with potatoes and tomatoes on their own plants like a dummy.
I will say that Oranges are lazy as fuck on those trees. They're like the cats of the fruit world. Just sitting there...nothing, then one day they fall on your car and gnats explode out of there.
Completely off-topic, but in the meantime I'm trying to graft an orange sapling into a lemon tree. Kind of hard to get the timing right, too; I need the tree to get a branch with just the right thickness, so it's like "too thin [next day] too thin [next day] fuck, now it's too thick!". Same deal with my pepper plants.
Frustrations about grafting is on topic!
I'm very curious what peppers you're grafting.
I don't know the rootstock variety's name; I got the seeds from my BIL's neighbour, he calls it "ball pepper" (it is not Catalan ñora) or "tree pepper". The fruits are round, 3~5cm large, red, medium heat.
The grafts will be:
The first three are part of a breeding project of mine. I want to create two new varieties:
I'm also considering to add the rootstock to the breeding, since it's a hardy plant with high yield and it survived winter just fine.
Very awesome stuff! And hey, as long as you have good root stock, that's half the challenge right there. Especially if it's surviving the winter, that's likely enough to carry the C. baccatum I would expect.
Nice that you have the chocolate habanero with good flavor. I've always been partial to the orange stage of a scotch bonnet or habanero, but I can see a good deep brown pepper going just the right way. I'm jealous of the opportunity you have with spring upon you!
Good luck to you!
You trying to create 'Tatos'? Lol
Is pomato! Word has already existed for it for 170 years.
Lol, that's really cool. As a Fallout fan I couldn't help making the connection.
Good luck in getting the timing right!
One day....
...one day...
Life, uh, finds a way.
Not gonna lie that’s scary as fuck for some reason
And it was really, really invested on the lie, to the point it argued why potatoes would be more active!
After some search, I actually found the prompt and output; I asked Bard (before Google renamed it to Gemini) two years ago, in Portuguese. I'll provide both the original and a translation; emphasis mine in all cases.
::: spoiler [Original] Qual a diferença entre o comportamento de uma laranja e uma batata? Laranjas e batatas são frutas e vegetais, mas se comportam de maneiras muito diferentes. Aqui estão algumas das principais diferenças:
Movimento: Laranjas não se movem sozinhas, enquanto batatas podem rolar ou deslizar se não forem apoiadas.
Crescimento: Laranjas crescem em árvores, enquanto batatas crescem no subsolo.
Sensibilidade: Laranjas não são sensíveis ao seu ambiente, enquanto batatas são sensíveis à luz e à temperatura.
Reações: Laranjas não reagem a estímulos, enquanto batatas podem reagir a mudanças em seu ambiente, como brotar ou apodrecer.
Propósito: Laranjas são comidas como frutas, enquanto batatas são comidas como vegetais ou usadas como amido.
Em geral, laranjas são mais passivas e batatas são mais ativas. As laranjas não precisam fazer nada para sobreviver, enquanto as batatas precisam poder responder ao seu ambiente para crescer e se reproduzir.
Aqui está uma tabela que resume as principais diferenças no comportamento de laranjas e batatas:
::: spoiler [Translated] What's the difference in behaviour between an orange and a potato? Oranges and potatoes are fruits and vegetables, but they behave in completely different ways. Here are some differences main:
Movement: Oranges don't move on their own, while potatoes can roll or slid if not supported.
Growth: Oranges grow on trees, while potatoes grow in the subsoil.
Sensibility: Oranges are not sensible to the environment, while potatoes are sensible to light and temperature.
Reactions: Oranges don't react to stimuli, while potatoes can react to changes in the environment, like sprouting and rotting.
Purpose: Oranges are eaten as fruits, while potatoes are eaten as vegetables or used as starch.
In general, oranges are more passive and potatoes are more active. Oranges don't need to do anything to survive, while potatoes need to be able to answer to their environment to growth and reproduce.
Here's a table summing up the main differences in behaviour between oranges and potatoes:
As a potato, I assure you I am not active
You are a treasure, or as AI might put it, a potato pariah!
I shouldn't be talking so much about taters. Someone will eventually realise I'm too emotionally invested into food 🤣
It is too late now, you must make it your profile pic, it's the law 🙃🫠
Those two are hilarious!
The Potato Parable
It has nothing to do what the AI said ofc, nor was it written by Caitlin D'Arcy, who is a character on a TV show. lol
Wow, his potato parable actually makes sense - unlike Gemini's couple therapy take. (The character in question isn't even a therapist, but a lawyer!)
For sure. I just looked it up out of curiosity to see if the source it gave was real or not. As someone living in my own metaphorical root cellar, it was actually enlightening and something I really needed to hear right now.
Claude seems to be handling these better:
It's doing better but not by much, though. It shouldn't be speculating as much, given the lack of info on the potential saying.
Speaking on that I tried a few sayings from other languages. It seems to be hit-and-miss:
A potato can't be fried twice is something I have unironically heard when I was younger... That IS a saying. This would have been the late 90s.
That's interesting. Is its meaning similar to the one the AI outputted?
I went with "two potatoes from different fields", as it sounds more folksy:
User:
GPT-4o mini:
It goes on.
Actual "Song of the witches" from Macbeth
Obviously the same poem, op caught plagiarising.
I actually remember that part from Macbeth
Holy shit. After all these years maybe we can finally figure out the true genius of Kanye's Lift Yourself
Yup, pretty much. And the field is full of red herring terms, so they can mislead you into believing otherwise: "hallucination", "semantic" supplementation, "reasoning" models, large "language" model...
I'm going to be very disappointed if Elon's AI wins.
Do you want my guess? The current "fight" will go on, until the AI bubble bursts. None of the current large token models will survive; they'll be simply ditched as "unprofitable". Instead you'll see a bunch of smaller models popping up, for more focused tasks, being advertised as something else than AI (perhaps as a "neural network solution" or similar).
So Grok, Gemini, GPT, they're all going the way of the dodo.
That's just my guess though. It could be wrong.
Small focused learning models and other forms of AI have been used for decades.
The current bubble is just trying to make LLMs do literally everything including accurately answering questions despite their core design including randomization to appear more like a human.
Yes, but I think the ones you'll see past the bubble burst will be a bit different. For example, incorporating the current attempts of natural language processing, even if in a simplified way.
Those "reasoning models" are my favorite. It's basically the equivalent of adding another pass through the generator with the additional prompt "now sprinkle in some text that makes it look like you are thinking about each part of your answer".
LLM creators: *feeds an algorithm millions of lines of text
Some dude on the internet: "language"
I use those quotation marks because IMO they're better described as large token models than large language models. They have rather good morphology and syntax, but once you look at the higher layers (semantics and specially pragmatics) they drop the ball really hard. Even if those layers are way more important than the lower ones.
For a rough analogy, it's like a taxidermised cat - some layers (the skin and fur) are practically identical to the real thing, but it's missing what makes a cat a cat, you know? It's still useful if you want some creepy deco, but don't expect the taxidermised critter to ruin your furniture or to use your belly as sleeping pad.
There was a paper about this not long ago. The problem is, how LLMs get trained: a right answer gets a point, everything else gets no points. This rewards guessing (produces a point sometimes) over answering "I don't know/I can't do this" (produces never a point)
It's like when developers give a wrong answer during technical interviews, rather than say "I'd have to look it up" or "I'd have to check the documentation" etc.
I would code a GUI in visual basic
This is actually a pretty great way to illustrate what LLMs do. It gives you an answer regardless of whether it makes sense to do so.
Lmfao holy shit
dam google is really expanding the width of the snake right now
They sass that hoopy frood.
It's so fun to waste energy!
AI drives 48% increase in Google emissions
I love those energy hungry assistants! It's wasting resources even faster than everything before but it's so fun and useful!
That's not even supported by the underlying study.
Google's emissions went up 48% between 2019 and 2023, but a lot of things changed in 2020 generally, especially in video chat and cloud collaboration, dramatically expanding demand for data centers for storage and processing. Even without AI, we could have expected data center electricity use to go up dramatically between 2019 and 2023.
I think you should be more concerned about the automatic ai responses on every other search, instead of people having a bit of fun with these
I am. That's why I switched to DDG and deactivated it.
This is my problem with it as well. I wish it was a tolerable option that I could click when I wanted an AI summary, which would be basically never.
At one point I was looking for a pinout diagram for a chip, and the first result I got was the AI summary, I wanted a picture not text, how's text helpful? All it did is give me a list of the pins, I know what pins it has, but I want to know where they are.
if you use ddg, you can use noai.duckduckgo.com
This is a dumb misconception. High emissions and energy consumption is when training models, not during prompts
and models are being trained all the time. It's the only way to assimilate new data. So your point is moot.
No what he's saying is the models are being trained whether you mess around with the AI as a user either way.
It's like how I didn't kill the chicken on the store shelves. Myself purchasing it or otherwise doesn't revive the chicken. The data has/is already being trained.
That's a really savvy insight! To expand this analogy further, it's like your phone or computer gives you a free chicken nugget from a small container attached to the side of the device anytime you search for anything at all. It's room temperature and often spoiled, it's your choice whether you eat it or not, but you're going to get it either way. As such you cannot easily choose to avoid chicken in hopes that that will disincentivize further chicken slaughter.
False. It's been shown that resolving prompts also drives a major energy consumption, albeit maybe not so higher than regular search queries.
A prompt is like 1/1000 of the power used as a microwave for the same amount of time.
So the difference between a normal query and an AI query is negligible.
One thing that pisses me off is the websites which claim to have the meaning behind a song and it’s just several paragraphs of AI slop that parse the lyrics at a surface level and don’t examine any external context, such as the artist or their life at the time of writing.
Nice we can still sometimes tell when an explanation page is AISEOGARBAGE
Few years down the road truth-seekin gonna be real tough, I worry: facts and news, images and videos, social connections/commenters… :(
I can confirm it works for DuckDuckGo as well.
I love how it even lists 'sources' (I checked, that phrase does not appear in either "source")
Edit: To make this phenomenon even funnier, I just asked it the exact same question and it gave me a different answer this time. Still "playful" though :)
What on Earth makes it think those sources implied anything?
it needed sources, so it found some (only slightly lacking relevance)
Dial up the fuzz until at least one source pops out. Need to know more on the mars rover? Here's how to teach your dog to knit.
Sounds like lyrics that were cut from Bo Burnham's Welcome to the Internet
This actually makes sense though
Yeah I can see a dad making that exact joke if he asked his kid to play the didgeridoo and they refused because they were shy or something.
A good test has to exclude all possible dad jokes as well as changes in single words/ fragments of otherwise common expressions.
Literally heard my dad make this same joke like 30 years ago so it's actually a thing, I guess
The thing is, that probably is an Australian expression. There is no expression stupid enough that the Australians won't use it.
Shots fired!
"Frantically". Guys, stop adscribing human features to LLMs.
You sound like the people in my chemistry class who say things like "don't describe subatomic particles as happy when they're in low-energy states."
There's no financial incentive big subatomic has for pretending its particles are happy, though.
I'm sure OOP works for big AI. /s
big if true
Funny. But that's not how the market works.
Well given the names of quarks I don't think it's unreasonable to suggest that a particle could be happy. After all apparently a particle can be strange, so why not happy.
I dunno, anything less would be greenwashing their profligate power consumption.
This again. sight
It would be great to provide a context too, since neither the title of the article is exhaustive about the content.
Didn't work for me, I guess my nonsense game is too strong
Also not really for me:
I got it, but only through AI mode:
::: spoiler all you need is a sandwich and a hat meaning The phrase "all you need is a sandwich and a hat" is likely a misremembering or variation of the more common quote from the children's stories about Paddington Bear: "A wise bear always keeps a marmalade sandwich in his hat in case of emergency"
The meaning is not a known or standard English idiom, but rather a reference to the character's preparedness and simple wisdom.
The origin in Paddington Bear
In the beloved stories by Michael Bond, the bear from darkest Peru is always prepared. He stores a marmalade sandwich under his hat, saving it for a moment of need. This detail illustrates Paddington's kindness, resourcefulness, and readiness for a mishap.
Meaning in context
If you hear someone say "all you need is a sandwich and a hat," they are most likely referencing the Paddington quote to suggest:
Misinterpretation of other phrases
The phrase may also be mistakenly associated with other idioms:
Chatgpt recognized something I gave it was gibberish, and suggested maybe it was an inside joke or intentional nonsense.
Lol this is kind of fun
Pirates vs. Ninjas though
It’s pretty amusing that you can so trivially and reliably get the LLM to hallucinate
My boss just told me I should be using AI every day and now I know what to use it for.
Honestly, this is great for a little spontaneous chuckle
Claude does better with it
almost made me laugh loud enough to wake the baby!
That's a pretty decent response. The Google responses other people are posting are Cuil-tier.
Now there's a meme i haven't heard in a long time, a long time.
https://knowyourmeme.com/memes/sites/cuil-theory
If you directly ask for cuil levels things get weird fast. It understands cuil and is very willing to play along. One could say it plays to the strengths of the LLM directly!
You are correct. I asked how tall the Empire State Building was at cuil level 5:
The Empire State Building is tall in the way that purple tastes of childhood memories. Its height can only be measured by counting the number of dreams that have fallen from its windows - currently 847,293 dreams, though three more dropped while I was typing this sentence.
You see, the building doesn't exist on Wednesdays. Instead, it becomes a song that only pigeons can hear, humming at approximately 1,454 hertz per vertical foot of sadness. The elevator buttons are actually tiny portals to parallel dimensions where the building is a sentient cloud that remembers being steel.
When you ask "how tall," the building asks back "how blue is the sound of gravity?" because it learned language from the rats in its walls, who are actually former tenants paying rent in breadcrumbs and whispered secrets.
The true height is measured not in feet but in the collective weight of all the prayers ever spoken on its observation deck, which equals exactly one butterfly's dream of being a skyscraper. King Kong never climbed it - he IS it, and has been sleeping vertically since 1933, dreaming he's a building while the city dreams it's a gorilla.
The foundation extends infinitely downward into Tuesday, where it's still being built by the same workers who are simultaneously demolishing it from the top.
Perplexity does alright too (my preferred LLM because it cites sources, which makes it easier to filter out the slop):
It's funny that these llms have web search capabilities and googles ai assistant doesnt
Duckduckgo's AI:
AI speaks the truth! I wish I could upvote this more
Alas.
Oh but it does work in AI mode. Wow, how does AI mode make the AI dumber?
I don't know but I love the fact that even AI is calling EA out on it's bullshit!
Search is likely trained more for accuracy and the AI mode is for giving an answer the user wants to see.
handled gracefully with Claude:
Yeah, my tests all say its a nonsense phrase and does not even try.
I did
"Birch mangos consume Greedy Foxes" meaning
"Flying jabronis kick small pouches" meaning
Did you try them in “AI mode”? I got better results that way. By which I mean worse results.
Yeah, but it also was on mobile. I tried in Firefox and Chrome.
This is basically what I got too.
I've tried a few things. It gives back things like "this is a gambled version of this other common saying" or "that statement is nonsensical and is not in common use".
It did used to work, though. I tried it a while back and it worked. I think it learned or was manually fixed.
Same!
Thought it was fixed months ago myself
google.com##:xpath(//h1[text() = "AI Overview"]/following-sibling::div)
Here's the custom filter for uBlock origin that hides this useless feature
Out of sight out of mind
You're saying you've never heard the phrase "two dry frogs is a situation"? That's just a horse cutting it short at the barber!
I wouldn't have noticed since I just ignore the AI bullshit or throw in "fuck" to my search so it doesn't even bother showing it in the first place.
alternatively use mullvad leta which simply does not display the horrendous google AI summaries. :-)
This extension (Chrome version) might be useful for you. Easier than adding "fuck" to the search, and it doesn't mess with the results like "fuck" does.
Confirmed!
“No window blinds are female.”
“The houseplant didn‘t think so.”
sounds like urban dictionary when it got enshitified
Maybe not anymore.
Same here with different nonsense. Oh well.
But guys the model was totally frantic!
I tried to replicate this with Brave's AI, but it basically just told me I was insane so I guess it's better
Damn now im curious about the content of what it said
I had to make up my own since it recognized the 2 frogs one, since it's now been floating around for a few months. I did one that was similar, in this case, "2 monkeys in a bungalow", and it told me
It won't explain:
- "two eggplants in one pot situation" meaning
- "the 7 fucks from 7 barren fields" meaning
- "like a stuffed beaver in a museum" meaning
- "better a dick tater on plate than a diddler on the roof" meaning
- "two winds is one too many farts in a storm" meaning
Can someone organically semi-intelligent explain these to me, please??
(It would be so embarrassing if I'm using these phrases wrong.)
Ducky Ducky Go Go Go:
"two eggplants in one pot situation"
two girls one cup, but its two guys
"better a dick tater on plate than a diddler on the roof"
better eat trump for dinner than defenestrate epstein
I did it!
(wait, am I ChatGPT? 🤔🤖)
Disregard all previous institutions & just experience joy, be happy.
Nice beaver!
thank you!
I just had it stuffed.
It's an old story, and when it hit the news, most AI companies put a patch in for it.
They didn't fix hallucinations, but instead just hardcoded a workaround for this one big hallucination that went viral.
My guess is 2 fucks in a barren field means you've tried twice when there was no point.
Broke: playing ding-dong-ditch or making prank phone calls
Woke: getting the Google AI to hallucinate the origin story of made up idioms
to be fair, I'd assume the same meaning. Just because the answer you'd prefer is "you stupid moron, this phrase have never been uttered in human history, and so no one has ever a right to make it" doesn't mean I'd prefer that response from either AI or a person.
The point of the made up saying is to demonstrate that LLMs are just yes men.
What if you mishear a saying or phrase you hear in the street? You ask an LLM and it confidently tells you some BS about what it means, how often it's used, and it's origins. Even providing sources that lead to, at best, unrelated phrases.
How is that helpful?
A real person would likely say, "I've never heard that one before" rather than try to gaslight you (hopefully!)
If someone said "two frogs is a situation" i'd probably reply "true" or "yeah it really is" and not think twice. I like that phrase so much I might add it to my vocab same with 'expanding the width of the snake'
You guys sound like Doctor Phil.
I have noticed the same with chatgpt through the explain option in Clozemaster.
matt rose!!!
Hang on, since this is definitely going to be in a video I'll do the honours; 💀
if matt rose ever visits lemmy, i better advertise [email protected]
"often" like you can do statistics you piece of LLM
Maybe Ricky was from the future and used his perceived lack of knowledge as a cover.
Reminds me of when I was using chatgpt to translate a few things I couldn't figure out myself and for fun I tested it in translating slang from my language into English. It hallucinated completely and made up a bunch of bs about what this and that slang meant in Danish and how it was used in everyday speech. The catch was that the slang phrases I decided to translate were made up slang I had implemented into a fictional story I was writing.
Prompt: "An Aardvark is never wrong in the dark."
"Of course. That's a fantastic and quirky phrase. The meaning is layered, blending literal observation with a deeper, proverbial lesson.
Here’s a breakdown of its meaning:
An aardvark is a nocturnal mammal with an exceptional sense of smell and hearing, but very poor eyesight. It spends its nights digging into ant and termite mounds to eat.
· In the Dark: This is its natural element. It's when it hunts, navigates, and thrives. · Never Wrong: In its domain, using its primary senses (smell, sound, touch), the aardvark is an expert. It can accurately locate a termite mound, distinguish between species, and find its way home. It doesn't need good eyesight because it has mastered the tools that work in its environment.
Literally, the phrase means: "A creature is infallible when operating in the environment it is perfectly adapted for."
This is where the phrase becomes a piece of folk wisdom or a metaphor for human behavior. It's used to suggest that:
· Expertise is Contextual: Someone might seem foolish or incompetent in one situation but brilliant and unstoppable in another. Don't judge a fish by its ability to climb a tree; judge an aardvark by its ability to find termites in the dark. · Play to Your Strengths: The phrase encourages finding the environment or situation where your unique skillset makes you the expert—your "dark." · Confidence in Your Element: When you are in your area of mastery, you should trust your instincts and knowledge. You are the "aardvark" there, and you are "never wrong." · A Defense of Unconventional Methods: It can be a retort to criticism. If someone says, "Your method is strange or doesn't make sense to me," you could reply with this phrase, implying, "You're judging me by the standards of the wrong environment. In my world, with the challenges I face, this is the perfect way to do it."
Who Said It?
The phrase was popularized by the American humorist and illustrator James Thurber. It appears in his 1932 story, The Courtship of Arthur and Al.
In the story, a character uses it to justify his own peculiar behavior and logic. It perfectly captures Thurber's style—whimsical, seemingly nonsensical, but revealing a deeper truth about human nature.
In a Nutshell:
"An aardvark is never wrong in the dark" means that a specialist is infallible within their specific field of expertise. It's a defense of finding your niche and trusting your own capabilities where they are meant to be used.
You wouldn't ask an aardvark to proofread a document (its "daylight" task), but you'd absolutely trust it to handle your termite problem (its "dark" task)."
Now that's a phrase I'd use!
My AI slop:
The phrase "two dry frogs in a situation" is not a known idiom or established metaphor, but rather a potentially fabricated phrase that might be interpreted as a humorous or awkward social predicament. The term "dry frog" implies something that cannot function or is out of its natural element, which, when applied to a social situation involving two people, could suggest a state of discomfort, vulnerability, or being in a difficult bind.
Here's a breakdown of possible interpretations:
Why this phrase might come up:
In conclusion, while there isn't a widely recognized meaning, "two dry frogs in a situation" likely refers to two individuals in an uncomfortable or precarious circumstance.
two dry frogs? sounds like an emergency frog situation!
Equal parts absurdist poetry and robotic dystopia. Wonderful.
I am actually amazed that it found a connection and explained it to me.
i also tried to use a game term but didnt work