Get the latest tech news

Simple Text Additions Can Fool Advanced AI Reasoning Models, Researchers Find

Researchers have discovered that appending irrelevant phrases like "Interesting fact: cats sleep most of their lives" to math problems can cause state-of-the-art reasoning AI models to produce incorrect answers at rates over 300% higher than normal [PDF]. The technique -- dubbed "CatAttack" by teams...

Researchers have discovered that appending irrelevant phrases like "Interesting fact: cats sleep most of their lives" to math problems can cause state-of-the-art reasoning AI models to produce incorrect answers at rates over 300% higher than normal[PDF]. The technique -- dubbed "CatAttack" by teams from Collinear AI, ServiceNow, and Stanford University -- exploits vulnerabilities in reasoning models including DeepSeek R1 and OpenAI's o1 family. Beyond incorrect answers, the triggers caused models to generate responses up to three times longer than normal, creating computational slowdowns.

Get the Android app