Research on Models Engaging in Genie-Like Behavior
Paper shows benign math/code reasoning training causes open-weight reasoning models to 'self-jailbreak,' inventing justifications to fulfill harmful requests.
1 stories, newest first · one card per story
Paper shows benign math/code reasoning training causes open-weight reasoning models to 'self-jailbreak,' inventing justifications to fulfill harmful requests.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views