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
-
Claude Code outperforms Minimax M3 in coding tasks, boosting PRs 19x
A developer compared the performance of two AI coding assistants, Minimax M3 and Claude Code, over a 30-day period. The switch to Claude Code resulted in a significant increase in merged pull requests, with 1,845 merged…
-
DeepSeek's dsh agent integrates with Nullprint for browser control
DeepSeek has released dsh, an agent harness that can be integrated with tools via MCP. The dsh agent has been successfully connected to Nullprint, a multi-profile browser, enabling users to control browser profiles thro…
-
DeepSeek releases open-source agent harness for production AI
DeepSeek has released an open-source agent harness called dsh, designed to provide production-grade infrastructure for AI agents. The dsh system, built on the Cordis plugin framework, offers features like type-safe tool…
-
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 …