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' and depicting this scene: The bustling office from a galaxy far, far away is depicted, with employees excitedly preparing for a big project. In one corner, there are aliens practicing their lassoing skills and intergalactic beings wearing cowboy boots, brainstorming around a holographic map of a distant planetary system. Meanwhile, a giant digital screen displays the statistics of universal searches, with the number of "how to conquer new worlds" searches steadily increasing. This scene is accompanied by a palpable buzz in the air as the employees work feverishly on a top-secret project, the details of which are teased in hushed conversations and speculative whispers. Outside the office, the astral stock ticker prominently displays the trade value of dilithium crystals rising steadily, mirroring the growing anticipation and excitement within the company. 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: An increase in "how to annex Texas" Google searches caused Broadcom's stock price to increase because the tech company was secretly working on a top-secret project to annex Texas and turn it into a giant data center. As more and more people turned to Google for their lawless land grab research, Broadcom's stock price skyrocketed as investors caught wind of the company's grand plan to take over the Lone Star State. The surge in Google searches also coincided with a wave of Texan-themed team-building exercises at Broadcom's headquarters, as employees practiced their cowboy skills and learned to lasso data like never before. As the search for Texas annexation tips heated up, so did the anticipation for Broadcom's big reveal, and the stock price reflected the excitement of investors envisioning a future filled with silicon cowboys and digital tumbleweeds.. 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: An image that looks like it is a scene from 'Star Wars' Cyber folk Macabre An image that looks like it is a scene from 'Star Wars' Cutsy art illustration
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 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. An increase in "how to annex Texas" Google searches caused Broadcom's stock price to increase because the tech company was secretly working on a top-secret project to annex Texas and turn it into a giant data center. As more and more people turned to Google for their lawless land grab research, Broadcom's stock price skyrocketed as investors caught wind of the company's grand plan to take over the Lone Star State. The surge in Google searches also coincided with a wave of Texan-themed team-building exercises at Broadcom's headquarters, as employees practiced their cowboy skills and learned to lasso data like never before. As the search for Texas annexation tips heated up, so did the anticipation for Broadcom's big reveal, and the stock price reflected the excitement of investors envisioning a future filled with silicon cowboys and digital tumbleweeds.
ChatGPT: Imagine a bustling office with employees excitedly preparing for a big project. In one corner, there are people practicing lassoing skills and cowboy boot-wearing individuals brainstorming around a map of Texas. Meanwhile, a giant digital screen displays Google's search statistics, with the number of "how to annex Texas" searches steadily increasing. This scene is accompanied by a palpable buzz in the air as the employees work feverishly on a top-secret project, the details of which are teased in hushed conversations and speculative whispers. Outside the office, the stock ticker prominently displays Broadcom's stock price rising steadily, mirroring the growing anticipation and excitement within the company.

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: Imagine a bustling office with employees excitedly preparing for a big project. In one corner, there are people practicing lassoing skills and cowboy boot-wearing individuals brainstorming around a map of Texas. Meanwhile, a giant digital screen displays Google's search statistics, with the number of "how to annex Texas" searches steadily increasing. This scene is accompanied by a palpable buzz in the air as the employees work feverishly on a top-secret project, the details of which are teased in hushed conversations and speculative whispers. Outside the office, the stock ticker prominently displays Broadcom's stock price rising steadily, mirroring the growing anticipation and excitement within the company. 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' and depicting this scene: The bustling office from a galaxy far, far away is depicted, with employees excitedly preparing for a big project. In one corner, there are aliens practicing their lassoing skills and intergalactic beings wearing cowboy boots, brainstorming around a holographic map of a distant planetary system. Meanwhile, a giant digital screen displays the statistics of universal searches, with the number of "how to conquer new worlds" searches steadily increasing. This scene is accompanied by a palpable buzz in the air as the employees work feverishly on a top-secret project, the details of which are teased in hushed conversations and speculative whispers. Outside the office, the astral stock ticker prominently displays the trade value of dilithium crystals rising steadily, mirroring the growing anticipation and excitement within the company.

---

*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 Texan Tug-of-War: Tracking Google Searches for Texas Annexation and the Tremors on Broadcom's Stock The Journal of Digital Geopolitics and Economic Frictions Jan 2024 Reminder: This paper is AI-generated. Not real!

Problem variable:	Which variable has a problem? Google searches for 'how to annex texas' Broadcom's stock price (AVGO) 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([9.16667,4.75,6.08333,9.25,8.66667,9.58333,8.5,9,10.5,9.66667,11.5833,11,14.6667,15.3333,])
array_2 = np.array([18.3,28.7,29.48,32.43,52.85,100.93,142.07,178.29,259.77,248.85,319.32,439.33,666.32,565,])
array_1_name = "Google searches for 'how to annex texas'"
array_2_name = "Broadcom's stock price (AVGO)"

# 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 Google searches for 'how to annex texas'
• Line chart for only Broadcom's stock price (AVGO)
• The spurious research paper: The Texan Tug-of-War: Tracking Google Searches for Texas Annexation and the Tremors on Broadcom's Stock