Download png, svg

AI explanation

^{Show image generation prompt} Model: dalle-3
Prompt: An image that looks like it is a scene from 'Star Wars', depicting this scene: In downtown Grand Rapids, Michigan, the skyline is hazy with air pollution, while people on the streets can be seen wearing masks to protect themselves. Amidst the pollution, the Victoria's Secret store proudly displays the latest Annual Fantasy Bra, adorned with exquisite gemstones and intricate design. The bra's packaging prominently features a tagline, "Breathe Easy in Luxurious Fashion," hinting at its innovative air purification feature. Passersby pause to admire the bra, captivated by the idea of combining stunning luxury with a practical solution to the city's air quality issues. Enhanced Visual Depiction: A futuristic urban scene in downtown Grand Rapids, Michigan, under a hazy sky filled with air pollution. People are seen wearing sci-fi inspired masks as they go about their day. In the midst of the pollution, a lavish Victoria's Secret store is depicted, showcasing the exquisitely designed Annual Fantasy Bra in a gleaming glass display. The bra's packaging boasts an otherworldly air purification feature, hinting at a luxurious and practical solution to the city's air quality issues. Passersby stop to admire the high-tech accessory, blending opulence and innovation in a futuristic metropolis. 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: Air pollution in Grand Rapids, Michigan and Value of the Victoria's Secret Annual Fantasy Bra. 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: Cute 2D animation An image that looks like it is a scene from 'Star Wars' Concept art Oragami Sci-fi fantacy
ChatGPT: An image that looks like it is a scene from 'Star Wars'

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 Air pollution in Grand Rapids, Michigan and Value of the Victoria's Secret Annual Fantasy Bra, in the following situation: As air pollution in Grand Rapids, Michigan increased, it created a demand for fresher, cleaner air, prompting Victoria's Secret to release an even more extravagant and luxurious Annual Fantasy Bra that would somehow filter out pollution for the wearer. After all, who wouldn't want a bra that not only looks stunning but also doubles as an air purifier? It's the breast of both worlds!. Keep the description simple.
ChatGPT: In downtown Grand Rapids, Michigan, the skyline is hazy with air pollution, while people on the streets can be seen wearing masks to protect themselves. Amidst the pollution, the Victoria's Secret store proudly displays the latest Annual Fantasy Bra, adorned with exquisite gemstones and intricate design. The bra's packaging prominently features a tagline, "Breathe Easy in Luxurious Fashion," hinting at its innovative air purification feature. Passersby pause to admire the bra, captivated by the idea of combining stunning luxury with a practical solution to the city's air quality issues.

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: [ An image that looks like it is a scene from 'Star Wars' ] and depicting this scene: In downtown Grand Rapids, Michigan, the skyline is hazy with air pollution, while people on the streets can be seen wearing masks to protect themselves. Amidst the pollution, the Victoria's Secret store proudly displays the latest Annual Fantasy Bra, adorned with exquisite gemstones and intricate design. The bra's packaging prominently features a tagline, "Breathe Easy in Luxurious Fashion," hinting at its innovative air purification feature. Passersby pause to admire the bra, captivated by the idea of combining stunning luxury with a practical solution to the city's air quality issues. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: An image that looks like it is a scene from 'Star Wars', depicting this scene: In downtown Grand Rapids, Michigan, the skyline is hazy with air pollution, while people on the streets can be seen wearing masks to protect themselves. Amidst the pollution, the Victoria's Secret store proudly displays the latest Annual Fantasy Bra, adorned with exquisite gemstones and intricate design. The bra's packaging prominently features a tagline, "Breathe Easy in Luxurious Fashion," hinting at its innovative air purification feature. Passersby pause to admire the bra, captivated by the idea of combining stunning luxury with a practical solution to the city's air quality issues. Enhanced Visual Depiction: A futuristic urban scene in downtown Grand Rapids, Michigan, under a hazy sky filled with air pollution. People are seen wearing sci-fi inspired masks as they go about their day. In the midst of the pollution, a lavish Victoria's Secret store is depicted, showcasing the exquisitely designed Annual Fantasy Bra in a gleaming glass display. The bra's packaging boasts an otherworldly air purification feature, hinting at a luxurious and practical solution to the city's air quality issues. Passersby stop to admire the high-tech accessory, blending opulence and innovation in a futuristic metropolis.

---

*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

Aerial Adversities: Analysing the Association between Air Pollution in Grand Rapids, Michigan and the Value of the Victoria's Secret Annual Fantasy Bra The Journal of Eclectic Environmental Economics Jan 2024 Reminder: This paper is AI-generated. Not real!

Problem variable:	Which variable has a problem? Air pollution in Grand Rapids, Michigan Value of the Victoria's Secret Annual Fantasy Bra 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([14.2077,16.7123,23.5616,53.022,50.8197,55.6164,49.589,50.137,42.8962,50.411,35.3425,47.5275,42.4658,23.8356,24.1096,29.589,35.7924,29.589,31.5068,29.0411,24.8634,22.1918,20,18.3562,])
array_2 = np.array([1000000,3000000,5000000,10000000,15000000,12500000,10000000,11000000,10000000,12500000,6500000,4500000,5000000,3000000,2000000,2500000,2500000,10000000,2000000,2000000,3000000,2000000,1000000,2000000,])
array_1_name = "Air pollution in Grand Rapids, Michigan"
array_2_name = "Value of the Victoria's Secret Annual Fantasy Bra"

# 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 Air pollution in Grand Rapids, Michigan
• Line chart for only Value of the Victoria's Secret Annual Fantasy Bra
• AI-generated correlation image
• The spurious research paper: Aerial Adversities: Analysing the Association between Air Pollution in Grand Rapids, Michigan and the Value of the Victoria's Secret Annual Fantasy Bra