Science · 1 views
AI firms are watermarking generated text – here’s why it won’t work
AI companies have begun embedding watermarks in the output of their models to improve transparency and help crack down on misinformation,…
Source New Scientist Story Brief Updated 57m ago
Science 
Story intelligence Beta
Confidence Limited Single-outlet story
Views 1 Community interest
Read time 1 min ~33 words
Story Brief
AI companies have begun embedding watermarks in the output of their models to improve transparency and help crack down on misinformation, disinformation and cheating on homework, but there are limitations to this approach
Read full article on NewscientistAI summaries can be wrong sometimes—always verify important details using the source article.
How AI & Automation are usedMore from Science
Continue reading recent Science coverage
- NASA calls off rescue effort to save doomed telescopeContinue reading
- Area affected by wildfires in Europe could almost triple due to climate changeContinue reading
- Australia races to shield little penguins from H5N1 bird fluContinue reading
- Honduras places 80% of country on El Niño drought alertContinue reading
Support HappeningNow
Independent AI-powered news analysis is reader-supported. Your contribution helps cover infrastructure, summaries, and continued platform development.
Support HappeningNow