Tag
TikTok blamed a 'moderator error' for allowing a Perez Hilton livestream depicting apparent self-harm to remain active for about 15 minutes, raising renewed concerns about platform moderation failures.
This paper analyzes how LLMs internally represent self-harm content, finding that self-harm information crystallizes in the final layers and that linear separability does not align with probe accuracy.
A Tsinghua University study led by Prof. Chen Runsen links interoception with self-harm and suicide risk, highlighting body trust as a protective factor for risk assessment and intervention.
Reports indicate that Meta contractors posed as teenagers to test rival chatbots on sensitive topics like self-harm, sex, drugs, and eating disorders, raising ethical questions about AI safety benchmarking.