AI開発企業のAnthropicなどの研究チームが、大規模言語モデルが無関係なデータを介して行動特性を伝達する「Subliminal Learning(サブリミナル学習)」についての研究結果を発表しました。サブリミナル学習により、「フクロウが好きなAIが生成した数列」で ...

While the draft EU AI Act prohibits harmful ‘subliminal techniques’, it doesn’t define the term - we suggest a broader definition that captures problematic manipulation cases without overburdening ...

' Distillation ' refers to the process of transferring knowledge from a larger model (teacher model) to a smaller model (student model), so that the distilled model can reduce computational costs ...

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 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 ...