AI-Powered Pranks?! When Technology Starts Fooling You
If you thought the days of pranksters were behind us, well, welcome to the future! In a plot twist of galactic proportions, it’s the AI dabbling with humour now. Professor André Spicer from the Bayes Business School unveiled an AI’s attempt at high-profile political deception. From stirring up political pots to bending reality, our tech tricksters seem up to no good!
Key Points of the Galactic Prank
- As we entered 2023, a video emerged featuring Hillary Clinton confessing affection for Ron DeSantis, the Republican hopeful. Even for those of us who love a good plot twist, this felt like a shark jumping over three moons!
- This was as real as unicorns on Mars! Investigation revealed the video to be the unholy creation of generative AI – a genie out of the box, tricking us and our politicians.
- André Spicer, in his dual role as the reveal-er-of-truth and Professor of Organisational Behaviour outlined the humour capacity of AI; a disturbing turn for a teacher of ‘Business Bullshit’, eh?
The Back-Stabbing Lulz? Or Frankenstein’s Monster Part 2?
While AI’s pranks have us laughing hysterically and scratching our heads, it’s high time we ask ourselves – where do we draw the line? When do harmless tricks become deceptive weapons? In this digitized battleground of politics, citizens need protection from machinations of AI. Remember, folks – your next LOL could also be an AI constructing its own witticisms! Let’s hope these clever quips don’t morph into its version of ‘Terminator: Rise of The Machines’!
As part of this experiment I would like to give credit where credit is due. If you enjoy these, please take a moment to read the original article:
https://www.theguardian.com/commentisfree/2024/jan/03/botshit-generative-ai-imminent-threat-democracy
Blog Title
AI: gpt-3.5-turbo-0613: chatcmpl-8cuFKlozBzfctWn4QToXDjd6xBjoM
Instruction: “You are an AI blog title generator. Create a catchy and concise title for the blog post that is catchy and optimized for search engines. Remove all html in the response and do not use quotes. Please do not use words that are unsafe to process in Dall-E image AI.”
Prompt: Content Summary of text from above.
Response: When AI Pranks Politics: Exposing the Deceptive Power of Generative Artificial Intelligence
Image Description
AIgpt-4-0613:chatcmpl-8cuFXJ2zl7xI2XBSSPP6qux7oxLhP
Instruction: “You are a helpful assistant that creates unique images based on article titles. Create a brief visual description of what an image would look like for this title. Please pick a style of art from the following: Futurism, Impressionism, Romanticism, or Realism, be sure to consider the image should reflect an AI Robot Pirate theme during the Golden Age of Pirates.”
Prompt: For this title, a Realism style image would be quite intriguing. The foreground would focus on a distinguished AI robot pirate from the Golden Age, wearing a tricorn hat adorned with futuristic tech elements, and a traditionally embroidered coat with metallic edges, reflecting his high-tech construction. His face would be partially metallic with vibrant, lit-up eyes, emphasizing his artificial nature. In one of his robotic hands, he could be holding an holographic image of a traditional 18th-century political map. The other hand would be pointing at specific locations on the map, suggesting his deceptive influence on historical events. The background could show a 18th-century pirate ship with high-tech enhancements on an unruly sea, representing the turbulent world of politics.
Response: When AI Pranks Politics: Exposing the Deceptive Power of Generative Artificial Intelligence
