New side quest unlocked:
Just soldered my first components to a PCB and have to admit it’s not that much different from wound cauterization

Looking forward to meeting everyone there #wwdc24

We are conducting a research study on medical students' perspectives and usage of AI Large Language Models (LLMs). If you are a medical student anywhere in the world and are interested in contributing your experiences, complete our anonymous survey.

rb.gy/2urfjz

This is similar to how I found Eric Steinberger. He was just an undergrad, but he did research on his own and put a solo paper on arxiv that followed up on my work. I was impressed, so I invited him to work with me. There's a lot of talent out there with non-traditional backgrounds.

When will folks realize all the aceing/passing X exams and glimpses of AGI papers are not papers but marketing brochures disguised as “science”?

It's like closed LLM companies took a dump on science and the rest of the community is going around with a bucket cleaning it up.

I heard it might be dropping next week?

50+ pages of technical jargon and overly complicated graphs just to obscure the fact that it’s RAG with langchain under the hood.

I will take no further questions on the matter.

Very orthogonal to my research focus but one of the coolest things I’ve seen in a while

I’m excited to share that I matched into The Osler Medical Residency ! Absolutely grateful for all the support Joanna Melia James Hamilton Johns Hopkins Gastroenterology & Hepatology Johns Hopkins IBD
American University of Beirut

Super proud of this recent publication describing early outcomes from a major clinical effort here at Stanford to minimize ischemia in heart transplantation! Many more exciting developments to come as we tackle this challenge! John W. MacArthur Brandon A. Guenthart, MD Stefan Elde, MD

Our annual 5k fun walk/run is almost upon us! If you live in the Bay Area, please come and join us on the beautiful Stanford campus!

If you don't, or can't make it, please consider donating to a very good cause that is close to all of our 'hearts' — Inherited Cardiovascular…

Incredibly excited to open-source a SwiftUI frontend and package for running OSS LLMs with Apple's machine learning framework, MLX.

Code available at Preternatural's GitHub linked below.

Happy to see that some of my original design contributions to swift-chat along with Pedro Cuenca have made it in other cool projects like Vatsal!

The current crop of generative AI applications in healthcare are only scratching the surface of what's possible. Documentation and question-answering are just the lowest hanging fruit.

Big models are still getting bigger, but on-device domain-specific models are the future, especially for privacy-first applications like medicine.

Here's a quick look at Notos to transcribe patient encounters entirely on device with the ability to export to any EHR like Epic.

Our clinical #NLP work just published in Nature Medicine! We present a framework to adapt & evaluate #LLM s for summarization. Physicians 🩺 prefer #LLM summaries to those of #medical experts❗

Big step to reduce documentation 📚 and focus more on personalized care 🙌

A 🧵

Blog post: swift.org/blog/mlx-swift/

MLX Swift
Docs: ml-explore.github.io/mlx-swift
Examples: ml-explore.github.io/mlx-swift/MLX/…
Code: github.com/ml-explore/mlx…

MLX C
Docs: ml-explore.github.io/mlx-c
Code: github.com/ml-explore/mlx…

.Roxana Daneshjou MD/PhD and I have been arguing this for a while now.

If you have to prompt your model a certain way to get good results on a benchmark, you’re just fitting to the benchmark, making it effectively useless.

Unsure what the long term vision of these medical scribing companies is, but transcription has become so commoditized you can recreate their core offerings privately and on-device entirely from scratch in about a day.
Here’s a demo from almost a year ago.

Regulators Alarmed by Doctors Already Using AI to Diagnose Patients trib.al/braFtcG