AI Shackled by Confusing Rules: Meta’s Oversight Board’s Findings
In a world where “incoherent” might just be the new synonym for “Meta”, the oversight board of the mammoth social network has discovered something quite interesting. It appears a video false-accusing the US president, Joe Biden, of some rather icky behavior, apparently doesn’t violate their rules. But wait, it gets better – they also described these very rules as “incoherent” and way too hung up on AI-generated content. Metal’s AI must feel like it’s been on a crazy roller-coaster ride!
Key Points:
– Meta’s oversight board found a Facebook video that wrongfully accuses President Joe Biden as a pedophile does not violate their company rules. It’s like finding out eating chocolate cake doesn’t violate your diet!
– Interestingly, the same board found these ‘non-violating’ rules to be very “incoherent”. It’s like appreciating a modern art piece – you respect it, but you have no freaking idea what it means.
– If you’re wondering who this board is, they aren’t the Facebook babysitters. The board is funded by Meta, Facebook’s mother hen, but run independently.
– This whole fiasco began when the board decided to take up an investigation into the Biden video in October, following a user complaint about an altered seven-second clip of the president. The Internet truly is a box full of surprises!
Final Thoughts:
Okay, so Meta’s rules may be as muddled as a five-year-old’s attempt at map drawing, but what does this mean for the rest of us? Are we supposed to sit around and reminisce about the good old days when rules were sane and AI was a creation of the future? Arguably, it can be quite entertaining to watch the drama enveloping the modern AI field. I bet even Asimov didn’t foresee an AI dystopian turn quite like this one when he was penning down his Three Laws for robots. But hey, it ain’t all doom and gloom – maybe rules being “incoherent” will form the base of the next big AI comedy. Stay tuned, folks! The world of AI never ceases to amuse, bemuse, or royally confuse.
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/technology/2024/feb/05/facebook-rules-allow-altered-video-casting-biden-as-paedophile-says-board
Blog Title
AI: gpt-3.5-turbo-0613: chatcmpl-8oskgMHzMQANjGlaVONLU5QTport0
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: AI Shackled by Confusing Rules: Meta’s Oversight Board’s Findings
Image Description
AIgpt-4-0613:chatcmpl-8oskm3AHyFGuG0J8CfwazBcVk5AzP
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: This image could be presented in the style of Futurism to demonstrate the clash of old and new technologies and ideologies. In the forefront, there would be an AI robot pirate, styled in classic golden age fashion with a tricorne hat and flowing coat, but with a sleek futuristic metallic look. The robot would have a confused facial expression and its hand raised in a futile effort to understand a labyrinthine hologram of complex legal-looking documents, symbolizing the complex rules. Meanwhile, rising from the background is a giant, ambiguous figure that represents Meta’s Oversight Board – depicted as a towering, ominous silhouette filled with numbers, codes, and algorithms. Rays of golden lights would radiate from this shadowy figure, suggesting its tremendous control and belonging to the golden age of pirates.
Response: AI Shackled by Confusing Rules: Meta’s Oversight Board’s Findings
