Don't miss the latest stories
Advertise Newsletter
Network
  • The Creative Finder
  • The Bazaar
  • Deals
  • Status Is Down
Community
  • Sign up / Log in
  • Discussion Forums
  • Calendar of Events
NEW

Follow

Share this

ChatGPT
AI Generators
Apps
Artificial Intelligence
Cybersecurity
Media
OpenAI
More
  • Productivity
  • Social Issues
  • Technology
  • UI/UX
  • Artificial Intelligence
  • Cybersecurity
  • Media
  • OpenAI
  • Productivity
  • Social Issues
  • Technology
  • UI/UX
MENU
  • Advertise with us
  • Submit tip/feedback
  • Work with us
  • Subscribe to newsletter
  • Subscribe to RSS
Advertise here
Advertisement

OpenAI Has A Secret ‘Text Watermarking’ Tool To Spot ChatGPT-Written Copy

By Mikelle Leow, 05 Aug 2024

Subscribe to newsletter
Like us on Facebook

Photo 308874081 © Dennizn | Dreamstime.com

 

OpenAI, the tech giant behind ChatGPT, has been quietly developing a text watermarking tool that could potentially put the kibosh on AI-assisted academic dishonesty.


The Wall Street Journal recently unveiled OpenAI’s internal tug-of-war over this text watermarking technology, with the latter later confirming the project in an updated blog post. This method involves embedding subtle markers within AI-generated text, creating a digital fingerprint that points back to ChatGPT.


While OpenAI reports that text watermarking has shown “highly accurate” results in certain scenarios, it’s not without its weak spots. The system struggles when faced with tampering techniques such as translation, rewording, or character insertions.

Advertisement
Advertisement


The ethical implications of text watermarking have sparked some debate within OpenAI. There are concerns that this technology might unfairly impact non-native English speakers who use AI as a legitimate writing aid. This potential for unintended discrimination has supposedly given the company pause, as it carefully weighs the broader societal impacts of implementing such a system.


OpenAI’s approach extends beyond just text watermarking. The company is also prioritizing the development of authentication methods for audiovisual content while exploring other text provenance tools.


Despite the potential benefits of text watermarking, not everyone is on board. A survey revealed that nearly 30% of surveyed ChatGPT users have reservations about the technology. Their primary concern is that visible watermarks might discourage people from using ChatGPT altogether, potentially stifling the adoption of AI writing tools for legitimate purposes.


While text watermarking may not be a perfect solution, it represents a significant step for the way ethical considerations are being hardwired into the AI era.

 

 


[via Engadget, Wall Street Journal, NewsBytes, cover photo 308874081 © Dennizn | Dreamstime.com]

Receive interesting stories like this one in your inbox
Advertise here

More related news

Advertise here
Also check out these recent news
Web Design
Link to news page

When Your Website Goes Down, This Is the Page Customers Meet Instead

2027
Link to news page

2027 Already Has A Color Of The Year And It’s Beginning On ‘Grounded’ Territory

IKEA
Link to news page

IKEA & Xbox Press Play On Furniture & Storage Inspired By The Iconic Controller

Fashion
Link to news page

Vogue Presents ‘United Flags of Fashion’ With Top Designers For All 50 States

Coca-Cola
Link to news page

Coca-Cola Pours Fresh Life Into Its Iconic Branding With Worldwide Redesign