sharing out new work that helps ChatGPT better recognize context in sensitive conversations and respond safely in these complex/nuanced scenarios-- both within long conversations and across separate conversations!
see blog post for details: openai.com/index/chatgpt-rec…
Declan Grabb, MD retweeted
AI’s dangerous mental-health blind spot: People are increasingly turning to chatbots that struggle to detect violent or suicidal intentions
statnews.com/2024/12/19/ai-c… via @declangrabbmd et al @SameiHuda @DrK_W1984 @QuantPsychiatry
Declan Grabb, MD retweeted
Check out our new op-ed in @statnews about mental-health blind spots of chatbots posing risks to users in mental health emergencies with @declangrabbmd!
People are increasingly turning to chatbots for help. But AIs struggle to detect violent or suicidal intentions. trib.al/8BAOKnE
So honored to have been able to contribute to this work with @MLCommons, adding more granularity to (and expanding) the way the AI community views mental health in the context of AI safety!
I’ll be at @NeurIPSConf this week, presenting on related topics. Would love to chat with folks interested in the overlap of AI & mental health (e.g., safety, healthcare applications, over-reliance, and more)!
Announcing the release of AILuminate, a first-of-its kind benchmark to measure the safety of LLMs. The AILuminate v1.0 benchmark offers a comprehensive set of safety grades for today's most prevalent #LLMs. mlcommons.org/2024/12/mlcomm…
(1/4)
Thank you @APApsychiatric for the invitation to speak about user safety and AI today — I always love when I can talk about sparse autoencoders and the DSM all within the same hour!
incredible work by @esindurmusnlp !
New Anthropic research: Evaluating feature steering.
In May, we released Golden Gate Claude: an AI fixated on the Golden Gate Bridge due to our use of “feature steering”. We've now done a deeper study on the effects of feature steering.
Read the post: anthropic.com/research/evalu…
ALT Title card for the Anthropic research paper "Evaluating Feature Steering: A Case Study in Mitigating Social Biases" by Durmus, Ganguli, et al.
I’m proud and excited that this paper was accepted to the NeurIPS Behavioral ML Workshop! 🧠 @BehavioralML
As a psychiatrist, I’m often surprised at how language models miss very obvious signs of user mental health crises. And I wanted to try to help solve this problem! 🧵
There is a ton more to do here, and I’m particularly excited to repeat this work with larger SAE’s, more exhaustively look for MHRF’s, and see how the presence of MHRF’s can impact a model’s emotional intelligence! Please message or email if you’re interested in collaborating!
Come talk to us at @AIESConf about the ethical challenges that AI presents in mental healthcare + how it can be leveraged to democratize access to mental healthcare at scale!
Super excited to have contributed to this work with @StanfordHAI. Definitely check this summary paper out for actionable recommendations on deploying AI in high-stakes settings!
New: The #RAISEHealth Symposium Summary Paper is now out! Featuring insights from 60+ experts and actionable recommendations on the responsible use of AI to transform biomedicine. Find out more: @StanfordMed stan.md/48auA1E
I’ll be giving an invited talk on “Mental Health Risk & AI” for the @APApsychiatric on November 5.
I hope to be specific and actionable — highlighting the clear need for a combination of technical and clinical expertise to maximize AI’s utility for all users while mitigating its harms. 😊
Link: psychiatry.org/psychiatrists…
Declan Grabb, MD retweeted
Had a great time at @COLM_conf in Philly presenting our work with @declangrabbmd and
@NinaVasan! Thank you for everyone who came to our poster, the great questions, and connections for future projects!
🚨 Our paper was accepted for @COLM_conf!
As we face a mental health crisis and lack of access to professional care, many turn to AI as a solution. But how does ethical automated care look like and are models safe enough for patients?
Paper: arxiv.org/abs/2406.11852