A Hilarious Tale of AI Chatbots, Copyrighted Favours, and a Vast Trove of Internet Data
In this good ol’ world of technology, things are getting steamier between artificial intelligence developers, particularly OpenAI (the cool kid who made that oh-so-flawless chatbot, ChatGPT), and the copyright authorities. OpenAI says it’s downright impossible to build suave tools like theirs without dipping toes in the forbidden pool of copyrighted material. And boy, do we have more to add to this tongue-in-cheek sauna!
Key Points aka The Tea, Served Hot!
- OpenAI claims it would be as impossible as teaching a dolphin to tap dance to create tools like ChatGPT without the alluring magic of copyrighted material. Heaven forbid anyone suggest training them with open source books, articles, and blogs!
- ChatGPT and its buddies in the AI space, including image generators like Stable Diffusion, behave a lot like ravenous puppies. They’re “trained” by feasting on mountains of data from the Internet, much of it wrapped appetizingly in the taboo blanket of copyright.
- Copyright, my dear Watson, is a legal defense against the scandalous misstep of using someone’s work without permission. You can’t just sashay off with someone else’s creation and pass it off as your own – that’s a faux pas, darling!
Final Thoughts aka The Last Laugh
It seems AI developers like OpenAI have hurriedly been caught with their hands in the proverbial cookie jar – grappling with the tension between desire and decorum in their utilization of copyrighted content. As the spotlight sharpens on this issue, only time will tell if they will find the balance between legitimate learning and legal lunacy.
To continue in their grand AI journey, they may have to tap into lesser-known quarters of the internet, or better yet, roll up their sleeves and create their own content for AI learning. A challenging prospect, one might say, but hey, even Sherlock had to solve a few tough cases before he became a legend, right? On this note, let’s sip on our teas and see how this hilarious drama of artificial intelligence training unfolds!
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/jan/08/ai-tools-chatgpt-copyrighted-material-openai
Blog Title
AI: gpt-3.5-turbo-0613: chatcmpl-8ekBndgPNsUl9huh62pZZmKtifdVH
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 and Copyright: The Battle for Training Data in the Age of Chatbots
Image Description
AIgpt-4-0613:chatcmpl-8ekBvBFpRpxYE6GYCTZqwylPrQh0R
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: A Futurism style artwork split into two halves. The left side is filled with old parchment maps, manuscripts, quill pens, and ink pots, signifying the traditional copyright systems. The right side is dominated by a futuristic AI Robot Pirate, symbolizing the new age of chatbots, with data streams flowing from its eyes reflecting images from the left side. It has a cutlass in one hand, held defensively, while the other hand is busily typing on a holographic keyboard. The Robot Pirate stands on a ship made from circuit boards and microchips, sailing on a digital sea, representing the training data. The contrast between the two halves highlights the conflict between the old and the new.
Response: AI and Copyright: The Battle for Training Data in the Age of Chatbots
