Models
New method aims to keep kids safe from illegal AI-generated content
Researchers developed an evaluation procedure that tests generative AI models for harmful capabilities without generating outputs. This could enable auditors to identify open-source models that have b
2 min lezen•Mit.edu•13 juli 2026
Researchers developed an evaluation procedure that tests generative AI models for harmful capabilities without generating outputs. This could enable auditors to identify open-source models that have been adapted to produce illegal content, like child sexual a…
Originele bron: Mit.edu