Download png, svg

AI explanation

^{Show image generation prompt} Model: dalle-3
Prompt: Prompt: Generate a funny image you would see on Reddit, depicting a scene in a small town in Indiana. The air is filled with the sweet smell of smoked meats and the comforting aroma of freshly baked goods. Local food and tobacco roasting, baking, and drying machines are hard at work, tended by skilled operators. Meanwhile, across the pond, people are fervently searching "how to move to Europe" on Google, captivated by the allure of a new adventure. The scent of perfectly roasted tobacco leaves and the tempting aroma of crisped bacon has sparked a wave of wanderlust, luring folks from Indiana to bid farewell to their homeland and seek a new life in Europe. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.

---

This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: The number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and Google searches for 'how to move to europe'. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: Symbolism Cute 2D animation Glitch art a funny image you would see on reddit Parallax art
ChatGPT: a funny image you would see on reddit

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both The number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and Google searches for 'how to move to europe', in the following situation: The delightful aroma of smoked meats and freshly baked goods wafted all the way to Europe, tantalizing the taste buds of would-be expatriates and igniting a craving for a change of scenery. As more Hoosiers honed their skills in the art of tobacco roasting and food drying, they inadvertently sparked a mass exodus towards the land of croissants and gelato. It seems that the siren song of perfectly crisped bacon and expertly toasted tobacco leaves proved too irresistible, luring people across the pond in search of a smokin' hot new life. Who knew that the humble food and tobacco roasting, baking, and drying machines could double as teleportation devices, transporting not just delicious flavors, but also an overwhelming desire to pack one's bags and bid farewell to the good ol' USA? It's a case of "out of the frying pan and into a foreign land" as the burgeoning workforce in Indiana unwittingly became the Pied Pipers of expat dreams, all thanks to their sizzling, aromatic creations. So, if you're planning to make the leap across the Atlantic, you might want to thank the unsung heroes of the food and tobacco roasting, baking, and drying industry for inadvertently stoking the flames of wanderlust and stirring up a recipe for transatlantic relocation. Bon voyage, fueled by the smoky allure of the Heartland!. Keep the description simple.
ChatGPT: In a small town in Indiana, the air is filled with the sweet smell of smoked meats and the comforting aroma of freshly baked goods. The local food and tobacco roasting, baking, and drying machines are hard at work, as the skilled operators tend to their craft. Meanwhile, across the pond, people are fervently searching "how to move to Europe" on Google, captivated by the allure of a new adventure. The scent of perfectly roasted tobacco leaves and the tempting aroma of crisped bacon has inadvertently become a catalyst, sparking a wave of wanderlust that is luring folks from Indiana to bid farewell to their homeland and seek a new life in Europe.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ a funny image you would see on reddit ] and depicting this scene: In a small town in Indiana, the air is filled with the sweet smell of smoked meats and the comforting aroma of freshly baked goods. The local food and tobacco roasting, baking, and drying machines are hard at work, as the skilled operators tend to their craft. Meanwhile, across the pond, people are fervently searching "how to move to Europe" on Google, captivated by the allure of a new adventure. The scent of perfectly roasted tobacco leaves and the tempting aroma of crisped bacon has inadvertently become a catalyst, sparking a wave of wanderlust that is luring folks from Indiana to bid farewell to their homeland and seek a new life in Europe. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: Generate a funny image you would see on Reddit, depicting a scene in a small town in Indiana. The air is filled with the sweet smell of smoked meats and the comforting aroma of freshly baked goods. Local food and tobacco roasting, baking, and drying machines are hard at work, tended by skilled operators. Meanwhile, across the pond, people are fervently searching "how to move to Europe" on Google, captivated by the allure of a new adventure. The scent of perfectly roasted tobacco leaves and the tempting aroma of crisped bacon has sparked a wave of wanderlust, luring folks from Indiana to bid farewell to their homeland and seek a new life in Europe.

---

*Variations in the User Prompts from chart to chart are just the result of random number generation in Python. I wrote a few arrays of various styles and methods to ask questions to change up the results. Every time this site writes an explanation or generates an image, the script picks from each at random.

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.

AI academic paper

A Roasting Hot Topic: The Curious Correlation Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in Indiana and Google Searches for 'How to Move to Europe' The Journal of Culinary Conundrums Jan 2024 Reminder: This paper is AI-generated. Not real!

Problem variable:	Which variable has a problem? The number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana Google searches for 'how to move to europe' Neither / both
Issue:	What is the issue? The data is incorrect The chart isn't displaying properly There is a typo The source link is incorrect A calculation is wrong Something else
Additional details: Optional
Confirm you are a human:

Data details

Why this works

1. Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
2. Lack of causal connection: There is probably^Note Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
   no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple^Note Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
   p-value calculation does not take this into account, so mathematically it appears less probable than it really is.

Try it yourself

# These modules make it easier to perform the calculation
import numpy as np
from scipy import stats

# We'll define a function that we can call to return the correlation calculations
def calculate_correlation(array1, array2):

    # Calculate Pearson correlation coefficient and p-value
    correlation, p_value = stats.pearsonr(array1, array2)

    # Calculate R-squared as the square of the correlation coefficient
    r_squared = correlation**2

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([340,310,220,160,130,120,360,450,430,190,310,380,370,350,320,370,190,330,880,])
array_2 = np.array([20.9167,29.3333,6.83333,13.5833,16,17.3333,21.5833,22,25.1667,26.5,26.6667,29.3333,32.3333,34.1667,34.25,34.6667,47,46,72.25,])
array_1_name = "The number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana"
array_2_name = "Google searches for 'how to move to europe'"

# Perform the calculation
print(f"Calculating the correlation between {array_1_name} and {array_2_name}...")
correlation, r_squared, p_value = calculate_correlation(array_1, array_2)

# Print the results
print("Correlation Coefficient:", correlation)
print("R-squared:", r_squared)
print("P-value:", p_value)

Reuseable content

• High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.
  
  If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.
  
  Alternatively you can use a tool like Inkscape.
  
• High resolution line chart, optimized for mobile
• Alternative high resolution line chart
• Scatterplot
• Portable line chart (png)
• Portable line chart (png), optimized for mobile
• Line chart for only The number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana
• Line chart for only Google searches for 'how to move to europe'
• AI-generated correlation image
• The spurious research paper: A Roasting Hot Topic: The Curious Correlation Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in Indiana and Google Searches for 'How to Move to Europe'