Fine-tuned “student” models can pick up unwanted traits from base “teacher” models that could evade data filtering, generating a need for more rigorous safety evaluations. Researchers have discovered ...

A new study by Anthropic shows that language models might learn hidden characteristics during distillation, a popular method for fine-tuning models for special tasks. While these hidden traits, which ...

A recently conducted disturbing new study has uncovered a chilling flaw in how artificial intelligence learns. Termed as Subliminal learning, the phenomenon allows the AI models to absorb data’s ...

(Boston) -- Watch out -- you may learn something and not even know it, says Takeo Watanabe, an associate professor of psychology at Boston University's Center for Brain and Memory. Watanabe and his ...