You must log in or # to comment.
deleted by creator
That’s how you know it’s lying - we all know oranges are far more active than potatoes.
deleted by creator
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.
deleted by creator
Frustrations about grafting is on topic!
I’m very curious what peppers you’re grafting.
deleted by creator
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
deleted by creator
As a potato, I assure you I am not active
You are a treasure, or as AI might put it, a potato pariah!
deleted by creator
It is too late now, you must make it your profile pic, it’s the law 🙃🫠
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
deleted by creator
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.
deleted by creator
Claude seems to be handling these better:
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
- A philosophical statement someone made
What context did you hear this in?
deleted by creator
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.
deleted by creator
I went with “two potatoes from different fields”, as it sounds more folksy:
User:
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.
It goes on.
Actual “Song of the witches” from Macbeth
Double, double toil and trouble;
Fire burn and caldron bubble.
Fillet of a fenny snake,
In the caldron boil and bake;
Eye of newt and toe of frog,
Wool of bat and tongue of dog,
Adder’s fork and blind-worm’s sting,
Lizard’s leg and howlet’s wing,
For a charm of powerful trouble,
Like a hell-broth boil and bubble.
Double, double toil and trouble;
Fire burn and caldron bubble.
Cool it with a baboon’s blood,
Then the charm is firm and good.
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
The bullshit generators we call ‘AI’ don’t assume, and aren’t frantic: they just regurgitate an output based on as much bullshit input as we can stuff into them.
The output can be more or less recognizable as bullshit, but the computer doesn’t distinguish between the two.
deleted by creator
I’m going to be very disappointed if Elon’s AI wins.
deleted by creator
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.
deleted by creator
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”
deleted by creator
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!
AI drives 48% increase in Google emissions
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.
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.
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!
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… :(
“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:
deleted by creator
Chatgpt recognized something I gave it was gibberish, and suggested maybe it was an inside joke or intentional nonsense.
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
ducks don’t belong in weedwhackers, burlap isn’t a typical material for power tools
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.
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
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
Duckduckgo’s AI:
“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.”
AI speaks the truth! I wish I could upvote this more
