#27 Exploring Claude Sonnet 3.7 for healthcare
Manage episode 468494977 series 3585389
Can Claude perform a range of complex clinical tasks? Dev and Doc are here to investigate.
Claude sonnet 3.7 was released less than 48 hours ago, the model is highly intelligent and is one of the best we have seen in recent memory. Definitely passes the vibe check.
We give some amazing examples of coding with claude with few shot prompts, and cover technical and clinical evaluations and share our first thoughts. We even tested claude to take a patient history!
NB - PLEASE don't do this at home, obviously this is a demo and we do not in any way condone or recommend using an LLM as your doctor or healthcare provider, we are just demonstrating what the future could be. If you are sick, please seek a medical professional.
👋 Hey! If you are enjoying our conversations, reach out, share your thoughts and journey with us. Don't forget to subscribe whilst you're here :)
TIMESTAMPS
00:00 start + highlights
01:54 Introduction
08:54 Benchmarks, state of the art
14:44 guardrails, refusals, AI safety and catastrophic risks
22:36 show and tell- great for coding and make video games!
26:54 example hospital runner
30:17 Medical use cases- clinical coding, biomedical entity extraction
37:04 only medical example in Claude model card- still hallucinating citations
38:37 making an anatomy app
40:10 forecasting clinical diagnoses
43:36 taking a medical history from a patient
53:33 wrap up
👨🏻⚕️Doc - Dr. Joshua Au Yeung - linkedin.com/in/dr-joshua-auyeung
🤖Dev - Zeljko Kraljevic twitter.com/zeljkokr
Spotify:podcasters.spotify.com/pod/show/devanddoc
Apple:podcasts.apple.com/gb/podcast/dev-and-doc-ai-for-healthcare-podcast/id1751495120
Substack:aiforhealthcare.substack.com
For enquiries - 📧 [email protected]
🎞️ Editor - Dragan Kraljević instagram.com/dragan_kraljevic
🎨 Brand design - Ana Grigorovici behance.net/anagrigorovici027d
28 episodes