Download png, svg

AI explanation

^{Show image generation prompt} Model: dalle-3
Prompt: [Scene: A bustling city street in Malta, filled with retro-style architecture and people walking around. The muted colors and dotted halftone pattern create a nostalgic vibe.] In the foreground, people are shown on their smartphones, with dotted speech bubbles emerging from the devices. The speech bubbles contain visuals of xkcd comics, each eliciting laughter from the individuals. The laughter emanates as dotted sound waves, blending with the city atmosphere. In the background, biogas plants are depicted with intricate details, showcasing the conversion of methane into biomass power. The plants exude energy, with dotted lines representing the transfer and utilization of power throughout the city. Overall, the scene evokes a retro, comic-book aesthetic, with the lively energy of the city and its gas-powered revolution taking center stage. 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 situation described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here is a situation: Because the increase in xkcd comics about social media led to a surge in laughter, which in turn caused an uptick in the production of biogas from all the methane released during the merriment. The increased biomass power generated in Malta is truly a gas-powered revolution!. Given that situation, which of the following image descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand and the tone of the explanation. Please respond with only one of the following potential descriptions: A scene from Skyrim A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s Photorealism Celtic art A black-and-white newspaper illustration
ChatGPT: A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated and the explanation described. Do not reference graphs or charts; describe physical objects.
User prompt: Please describe a visual scene that depicts the following situation. Keep the description simple. Because the increase in xkcd comics about social media led to a surge in laughter, which in turn caused an uptick in the production of biogas from all the methane released during the merriment. The increased biomass power generated in Malta is truly a gas-powered revolution!
ChatGPT: I see a bustling city street in Malta, where there is a sudden increase in the number of people reading xkcd comics on their smartphones. As they start laughing out loud at the comics, I notice an uptick in the number of biogas plants around the city. These plants are bustling with activity, and you can see them converting the released methane from the laughter into biomass power. The city is buzzing with energy, and it's truly a gas-powered revolution!

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 comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s ] and depicting this scene: I see a bustling city street in Malta, where there is a sudden increase in the number of people reading xkcd comics on their smartphones. As they start laughing out loud at the comics, I notice an uptick in the number of biogas plants around the city. These plants are bustling with activity, and you can see them converting the released methane from the laughter into biomass power. The city is buzzing with energy, and it's truly a gas-powered revolution! Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [Scene: A bustling city street in Malta, filled with retro-style architecture and people walking around. The muted colors and dotted halftone pattern create a nostalgic vibe.] In the foreground, people are shown on their smartphones, with dotted speech bubbles emerging from the devices. The speech bubbles contain visuals of xkcd comics, each eliciting laughter from the individuals. The laughter emanates as dotted sound waves, blending with the city atmosphere. In the background, biogas plants are depicted with intricate details, showcasing the conversion of methane into biomass power. The plants exude energy, with dotted lines representing the transfer and utilization of power throughout the city. Overall, the scene evokes a retro, comic-book aesthetic, with the lively energy of the city and its gas-powered revolution taking center stage.

---

*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

Can't Resist xkcd and Biomass: A Comic Study on the Power of Social Media and Renewable Energy in Malta Journal of Social Media and Renewable Energy Research Jan 2024 Reminder: This paper is AI-generated. Not real!

Problem variable:	Which variable has a problem? xkcd comics published about social media Biomass power generated in Malta 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([8,17,14,13,11,16,19,17,13,11,12,])
array_2 = np.array([0.005,0.009,0.006,0.007,0.007,0.008,0.01,0.009,0.006,0.006,0.007,])
array_1_name = "xkcd comics published about social media"
array_2_name = "Biomass power generated in Malta"

# 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 xkcd comics published about social media
• Line chart for only Biomass power generated in Malta
• The spurious research paper: Can't Resist xkcd and Biomass: A Comic Study on the Power of Social Media and Renewable Energy in Malta