AI models still struggle to actually see
Researchers at Moonshot AI created a new test called PerceptionBench. They wanted to see if AI models can truly understand images without relying on logic tricks. It turns out that most models are not as smart as they seem.
No model reached a score of 60 percent on this test. Even the top models struggle to identify basic details in pictures. This proves that many mistakes attributed to bad reasoning are actually just failures to see the image correctly.
This gap between seeing and thinking is a big problem for developers. Future AI will need to get much better at processing visual information. For now, you should be careful about trusting what an AI claims to see.
Comments (0)
No comments yet. Be the first!
More AI news
NewsGoogle AI Changes Its Search Advice After Bias Complaints
Google updated its search tool after it incorrectly told users to call emergency services based on a person's nationality.
NewsWhy AI Is Still Failing at Simple Tasks
Researchers gave an AI five thousand dollars to grow, but it could not even open a bank account.
NewsEnovis to Buy eCential Robotics
Enovis is expanding its surgical tech business by purchasing French company eCential Robotics.