News

Pornhub is using artificial intelligence to identify, tag porn star

Porn site Pornhub is now using artificial intelligence to identify and tag more than 10,000 porn stars in videos. The site previously relied on the users and uploaders to only manually encode.

Pornhub fed the new AI-model “a few thousand videos,” plus porn stars’ official photos. Pornhub users can then validate the AI-model results by upvoting or downvoting the tags. The company said that the model will improve and smarter as time goes on, because it “learns on the basis of what the community has validated.”

“Now, users can search for a specific pornstar, they have an affinity for and we will be able to get more precise results,” Pornhub Vice President Corey Price said in a statement.

The new model will “play a crucial role moving forward,” he added, because there are more than 10,000 videos are uploaded to the site every day. Pornhub is the testing of the model in beta for the past month; in that time, it was able to scan 50,000 videos.

More From PCmag

  • Exclusive: See Puerto Rico Networks Light, Drop Off

  • Mattel Launches Kamigami Build and Code Robots for Children

  • Amazon Offers Students Prime for $5.49 per Month

  • Porsche Launches sports car, SUV Subscription Program

In the coming year, Pornhub hopes for the scanning of all of the 5 million videos that are currently on the platform. The company is also planning to start with the use of this technology to tag specific categories and sexual positions seen in videos. So, if the AI model detects that a video is shot outside, it will automatically add it to the “Public” category for people who enjoy that sort of thing. Or, if it detects a blonde in the video, it will add to the “blonde” category.

“Artificial intelligence has quickly reached a fever pitch, with many different companies in which the opportunities considerably speeding up outdated processes,” Price said. “And that is exactly what we do with the introduction of our AI model.”

This article originally appeared on PCMag.com.

Follow us

Don't be shy, get in touch. We love meeting interesting people and making new friends.

Most popular