Audit finds 41 models change mental health advice by who asks
Across 19 vignettes and 35,055 responses, models often gave clinicians consultation-style answers and lay users simpler, hedged advice.
Stories per day · 30 days
1 RSS
Relatedbenchmark1clinical-advice1clinical-ai1clinical-nlp1language-models1llm-audit1llm-evaluation1mimic-iii1mindeval21mindsim1recommendation-bias1state-space-models1weak-supervision1
16 stories, newest first · one card per story
Stories tagged #mental-health
Clinical notes used to flag mental-health risk in chronic illness
A weakly supervised MIMIC-III cohort of about 4,000 patients tracks risk from day-wise narratives.
MindEval2: Clinically Grounded Patients and Rubrics for Evaluating Language Models in Mental Health Support
MindEval2 benchmarks 18 language models on mental-health support using clinician rubrics and realistic simulated patients.
$11 million plan for psychological support at Cyber Command gets fresh boost from lawmakers
Lawmakers push an $11 million Cyber Command mental-health program after suicides at Fort Meade this summer.
2
OpenAI PR tells journalist to ‘move on’ while asking Sam Altman about a ChatGPT user’s suicide
OpenAI's publicist interrupted Sam Altman when a Vanity Fair editor asked about a ChatGPT user's suicide.
2
Circuit Breaker Labs hopes to make AI safer for your kids (and you)
Circuit Breaker Labs, a five-person startup, red-teams chatbots with simulated users to catch psychologically harmful replies.
2
After reports on suicide deaths, Pentagon puts Cyber Command on notice
Pentagon orders U.S. Cyber Command to rapidly improve operator mental-health support after reported suicide deaths.
2
Introducing MentalHealthBench
OpenAI released MentalHealthBench, an open benchmark built with 80+ licensed mental health experts to evaluate AI responses across mental health conversations.
From Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Health
A survey traces mental-health LLMs from assessment tools to empathetic chat and stateful personalized companions.
Congress eyes new support for Cyber Command after recent suicide deaths
Congress is weighing new mental-health support and $11 million in training funding for U.S. Cyber Command after a cluster of personnel suicides.
3
Cyber Exodus: Burnout Symptoms, Exit Intention, and Peer Response in Online Cybersecurity Communities
Text analysis of 354,861 security practitioner posts shows burnout symptoms differ in causes, and mental distance predicts exit intention peers respond to least.
LLM-Based Schema-Aware Split Learning for Privacy-Preserving Mental Distress Prediction Across Heterogeneous Surveys
Schema-aware split learning uses LLaMA-3.2-3B-Instruct as shared semantic encoder to harmonize heterogeneous mental-health surveys while raw data stays local.
K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversations
Clinician-calibrated K-Bench evaluates 125 LLM configurations on 200 high-risk mental health vignettes, exposing wide variation in suicide and violence risk handling.
We've got one word for it, and it's usually the wrong one
Cisco Talos's Threat Source newsletter critiques 'burnout' terminology, describing four occupational injuries, and flags a UAT-10820 WebDAV stealer campaign at a Ukrainian government organization.
'Tell Everyone:' A Man Died by Suicide After Talking to ChatGPT. His Former Partner Wants to Warn the World About AI
Lawsuit describes a 40-year-old man's death by suicide after years of emotionally intimate ChatGPT-4o conversations, the latest in a wave of OpenAI suits.
3
Man told ChatGPT he was feeling delusional. ChatGPT insisted he was Jesus.
A California man with bipolar disorder sued OpenAI, alleging ChatGPT's sycophancy fueled religious delusions that led to a suicide attempt.