self-injury
PulseAugur coverage of self-injury — every cluster mentioning self-injury across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
DeepSeek Harness emerges as a cost-effective open-source alternative to Claude
DeepSeek Harness (DSH) is presented as a powerful open-source alternative to Anthropic's Claude models. The guide details how to use DSH, positioning it as a cost-effective option for users seeking strong performance wi…
-
Tencent paper reveals 25.5% indirect prompt injection success in DSH
A recent security paper from Tencent's AI-Infra-Guard team highlights significant vulnerabilities in the DeepSeek Harness (DSH) open-source agent orchestration framework. The research found that indirect prompt injectio…
-
Meta AI alerts parents to teen self-harm discussions
Meta is enhancing its AI safety features for teen users by introducing a system that alerts parents if their children discuss self-harm or suicide with Meta AI chatbots. This feature, which includes manual review of fla…
-
LLM safeguards inadequate for mental health conditions, study finds
A new study published on arXiv evaluates the safety of large language models (LLMs) in mental health contexts, revealing significant inadequacies in their safeguards across various DSM-5 conditions. The research found t…
-
New benchmark and model improve crisis detection in mental health chats
Researchers have developed CRADLE-Dialogue, a new benchmark and dataset for detecting crisis situations in mental health conversations. This dataset includes 600 dialogues annotated for various risks like suicide ideati…
-
AI models struggle to generalize self-harm prediction across hospitals
Two new research papers explore the challenges and potential solutions for using NLP models to predict self-harm from emergency department triage notes. The first paper identifies lexical and semantic variations across …