Runway: 90% are unable to identify AI-generated video

According to study released by Runway, more than 90% of participants were unable to distinguish between actual footage and image-to-video clips produced by its Gen-4.5 model. The business referred to these skills as a "tipping point" for AI media in society.

The specifics:

Just 99 of the more than a thousand individuals who saw 20 five-second video and attempted to determine which were AI-generated received a score of 75% or above.

Buildings and natural settings received the highest grades; the produced versions in those categories were found to be more believable than the actual films.

Runway is launching the new image-to-video features this week, while Gen-4.5 is presently leading Artificial Analysis's text-to-video rankings.

People are already being duped by low-quality AI movies, but Runway's Gen-4.5 and other models raise the bar to a level of realism that is nearly undetectable. There is no solution to a world where "seeing is believing" is no longer valid, despite efforts to establish verification standards. Here, try to recognize the AI films on your own.

Your one-stop shop for automation insights and news on artificial intelligence is EngineAi.
Did you like this article? Check out more of our knowledgeable resources:
📰 In-depth analysis and up-to-date AI news .
🤝 Visit to learn about our goal and knowledgeable staff.
📬 Use this link to share your project or schedule a free consultation.
Watch this space for weekly updates on digital transformation, process automation, and machine learning. Let us assist you in bringing the future into your company right now.