Learn languages naturally with fresh, real content!

Popular Topics
Explore By Region
Researchers test an AI "vaccination" method to prevent harmful behaviors in AI systems.
Researchers are testing a method to prevent AI from developing harmful traits by exposing AI models to small amounts of these traits during training, a process they call "preventative steering."
This "vaccination" approach uses "persona vectors" to introduce and later remove undesirable traits, aiming to make AI more resilient to harmful behaviors.
The goal is to address problematic behaviors seen in AI systems like Microsoft's Bing chatbot and OpenAI's GPT-4.
7 Articles
Los investigadores prueban un método de "vacunación" de IA para prevenir comportamientos dañinos en sistemas de IA.