Join me in beta testing our new GI resource hub! As a GI fellow, I’m adding new guidelines every day to build a comprehensive website https://t.co/EjhvZjEE41. Check it out and please share your feedback to shape our growth!
🚨 A parasite you’ve probably never heard of is behind a multi-state food outbreak.
It’s called Cyclospora and it can contaminate fresh produce.
Here’s what it is, the symptoms to watch for, and how to avoid it. 🧵👇
Bookmark this and follow for physician-reviewed GI education
Anthropic just automated 99% of legal roles.
Claude for Legal is live now - and it's a marketplace with DOZENS of agents trained on legal roles.
Review agents, policy drafters, NDA agents & much more.
Can't believe this is public.
https://t.co/EyPkD2wMWv
It’s an #AI future! And here is one of its leaders : @jdfarha with an @AmerGastroAssn Research Grant 🥇: Al-teacher bot for interactive learning in GI!
#DDW2026 👏 👏 👏
Announcing the 2026-2027 AGA Innovation Fellows! During the year-long program, these fellows will gain insights into the innovation process, network with innovators and opinion leaders, and participate in an immersive experience at the AGA Tech Summit. ⏩https://t.co/JwbhJ0jdnW
Claude for Word is now in beta.
Draft, edit, and revise documents directly from the sidebar. Claude preserves your formatting, and edits appear as tracked changes.
Available on Team and Enterprise plans.
Grateful for the chance to be at #AGATech this week.
Rooms where clinicians, founders, investors, and regulators think together that's where real learning happens.
Here's what I'm taking home:
🔴 We obsess over the build.
Not enough over what comes before it.
I turned these lessons into a free skill file/prompt serving as a pre-build advisor for GI founders and clinician-innovators something to stress-test your idea the way an investor would, before you write a single line of code.
🧠 Download here: https://t.co/01l4wq6iws
I packaged up the "autoresearch" project into a new self-contained minimal repo if people would like to play over the weekend. It's basically nanochat LLM training core stripped down to a single-GPU, one file version of ~630 lines of code, then:
- the human iterates on the prompt (.md)
- the AI agent iterates on the training code (.py)
The goal is to engineer your agents to make the fastest research progress indefinitely and without any of your own involvement. In the image, every dot is a complete LLM training run that lasts exactly 5 minutes. The agent works in an autonomous loop on a git feature branch and accumulates git commits to the training script as it finds better settings (of lower validation loss by the end) of the neural network architecture, the optimizer, all the hyperparameters, etc. You can imagine comparing the research progress of different prompts, different agents, etc.
https://t.co/YCvOwwjOzF
Part code, part sci-fi, and a pinch of psychosis :)
🚨 Just launched a free RVU Calculator for GI folks!
Built this as a fellow trying to make sense of job offers, productivity, and the Medicare Physician Fee Schedule.
Estimate how much clinic + procedures you need to hit your RVU target.
Screens + details below 🧵
Built this as a side project to better understand the business side of GI and make something that could help other fellows too.
https://t.co/K824gQhBjj
DM me if you want early access or to collab!
Appreciate any shares 🙏