Download png, svg

AI explanation

^{Show image generation prompt} Model: dalle-3
Prompt: Create an image of a breathtaking poppy field in Afghanistan, with workers harvesting the vibrant red flowers. In the distance, a bustling bakery is visible, where bakers are seen rolling out a fresh batch of poppy seed bagels. The image should capture the juxtaposition of the calmness of the field and the liveliness of the bakery, conveying the interconnectedness of these seemingly disparate scenes. The overall composition should evoke a sense of contrast and harmony, allowing for the viewer to contemplate the beauty and complexity of the world. 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: Afghanistan's Estimated Opium Production and Average number of comments on 3Blue1Brown YouTube videos. 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: Sci-fi fantacy Woodblock painting A scene from Skyrim Art nouveau Woodblock painting
ChatGPT: A scene from Skyrim

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 Afghanistan's Estimated Opium Production and Average number of comments on 3Blue1Brown YouTube videos, in the following situation: As opium production in Afghanistan increased, there was a corresponding spike in the worldwide production of poppy seed bagels. This led to a sudden surge in mathematical and geometric inspiration among viewers, prompting them to engage in more discussions and, you could say, a-MAIZE-ing comment threads on 3Blue1Brown's videos. The power of poppy-related puns and mathematical munchies should not be underestimated!. Keep the description simple.
ChatGPT: In a sprawling poppy field in Afghanistan, the estimated opium production rises, as workers harvest the vibrant red flowers. Meanwhile, in a bustling bakery across the globe, bakers roll out a fresh batch of poppy seed bagels, ready to be savored. As the bagels make their way to breakfast tables, viewers around the world are captivated by 3Blue1Brown's videos, engaging in lively discussions and sharing an abundance of poppy-related puns, fueled by the newfound inspiration from the mathematical and geometric intricacies explored in the videos.

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 scene from Skyrim ] and depicting this scene: In a sprawling poppy field in Afghanistan, the estimated opium production rises, as workers harvest the vibrant red flowers. Meanwhile, in a bustling bakery across the globe, bakers roll out a fresh batch of poppy seed bagels, ready to be savored. As the bagels make their way to breakfast tables, viewers around the world are captivated by 3Blue1Brown's videos, engaging in lively discussions and sharing an abundance of poppy-related puns, fueled by the newfound inspiration from the mathematical and geometric intricacies explored in the videos. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Create an image of a breathtaking poppy field in Afghanistan, with workers harvesting the vibrant red flowers. In the distance, a bustling bakery is visible, where bakers are seen rolling out a fresh batch of poppy seed bagels. The image should capture the juxtaposition of the calmness of the field and the liveliness of the bakery, conveying the interconnectedness of these seemingly disparate scenes. The overall composition should evoke a sense of contrast and harmony, allowing for the viewer to contemplate the beauty and complexity of the world.

---

*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

The Poppy and the Playlist: Unearthing the Unlikely Link between Afghanistan's Opium Production and 3Blue1Brown YouTube Engagement The Journal of Unconventional Interdisciplinary Studies Jan 2024 Reminder: This paper is AI-generated. Not real!

Problem variable:	Which variable has a problem? Afghanistan's Estimated Opium Production Average number of comments on 3Blue1Brown YouTube videos 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.
4. Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.

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([3300,4800,9000,6400,6400,6300,6800,6200,])
array_2 = np.array([1625.43,1850.58,4168.82,2696.38,3049.93,2365.29,2178.14,3570.88,])
array_1_name = "Afghanistan's Estimated Opium Production"
array_2_name = "Average number of comments on 3Blue1Brown YouTube videos"

# 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 Afghanistan's Estimated Opium Production
• Line chart for only Average number of comments on 3Blue1Brown YouTube videos
• AI-generated correlation image
• The spurious research paper: The Poppy and the Playlist: Unearthing the Unlikely Link between Afghanistan's Opium Production and 3Blue1Brown YouTube Engagement