What Does OpenAI’s ChatGPT Think About Copyright? - Priori

What Does OpenAI’s ChatGPT Think About Copyright?

By Priori Legal
| Legal Industry Technology

22-12-14 ChatGPT Blog Post

We asked the trending chatbot to discuss the copyright implications of its existence

If you’ve been on the internet in the past couple of weeks, chances are you’ve come into contact with ChatGPT, a chatbot recently launched by artificial intelligence (AI) company OpenAI. If you’re not familiar, the concept is simple: You feed the chatbot a prompt and then it generates text using an AI-enhanced algorithm to give you its best answer. The answers are usually basic but, depending on the prompt you give it, also remarkably human. 

In the legal industry, there are a number of conversations going on about ChatGPT, not the least of which is whether it can eventually replace attorneys. A recent Reuters article looked into just that question, and echoed the conclusion from a conversation during a Priori webinar—while AI-generated text may eventually be an option for rote legal work, it isn’t likely to replace the complex work attorneys do any time soon. 

Copyright Concerns

Whether AI-generated content can run afoul of copyright laws is another common question about the technology. Because ChatGPT or image-generating apps like Lensa AI are often trained on publicly available works, could a technically new image that is created by AI cribbing from an already-existing image be an infringement? Law.com recently analyzed the issue with regard to images created by Lensa AI and explained that “we are far from having a final word on whether training AI models on copyrighted material in datasets constitutes copyright infringement.”

So we decided to ask the bot itself what it would say about copyright concerns in light of its existence. We asked ChatGPT to: “Write a blog post about the copyright implications of ChatGPT.” Here is the result:

As a large language model trained by OpenAI, ChatGPT is an incredibly powerful tool that has the ability to generate human-like text on a wide range of topics. However, like any technology that can produce original content, ChatGPT raises some important questions about copyright.

In general, copyright law protects original works of authorship, such as writing, music, and art. This means that if ChatGPT produces something that is sufficiently original and creative, it could potentially be eligible for copyright protection.

However, there are a few key factors that would need to be considered in order to determine whether or not ChatGPT's output is eligible for copyright. One of the most important factors is the level of human involvement in the creative process. If a human were to heavily edit or curate ChatGPT's output, then it's possible that the resulting work could be eligible for copyright.

Another factor to consider is the question of whether or not ChatGPT's output is truly original. While ChatGPT is incredibly sophisticated and can produce text that is difficult to distinguish from human-written content, it is ultimately still generated by a machine using pre-existing data. This means that it is unlikely that ChatGPT's output would be considered truly original, and therefore not eligible for copyright protection.

Overall, while ChatGPT is a powerful tool that has the potential to produce some truly impressive content, the question of its copyright eligibility is a complex one. It's ultimately up to courts and legal experts to determine whether or not ChatGPT's output can be protected under copyright law. In the meantime, it's important for users of the technology to be aware of the potential legal implications of using it to generate original content.

AI Analyzing Its Future

ChatGPT’s response is impressive. It’s readable and it makes sense, which probably doesn’t come as a surprise to anyone who has tinkered with the chatbot themselves. However what is surprising about this particular response is the chatbot’s fair appraisal of its own power. In addition to calling itself a “powerful tool” for “truly impressive content,” it also smartly decides that the final decision on copyright and AI-generated content should be left “to the courts and legal experts to determine.” Regardless of how much humans come to depend on iterations of AI generation over the next months and years, it is probably a correct prediction that legal experts across the spectrum will weigh in and courts will see it come across their dockets.


You may also be interested in...
Like what you’re reading?
Sign up to get updates.