Ryan Stewart retweeted
First base coach talking to a runner: "Ok so stay here until you can go to the next one. If you get to that one try to get to the third one. A colleague of mine is waiting there for you"
Ryan Stewart retweeted
As physicians we have taken an oath.
To put the patient first.
To act in their best interest.
To uphold the highest ethical standards.
The people running insurance and pharmaceutical companies have not taken the same oath.
They care most about making profits for their shareholders.
Yet, their business decisions affect how we practice medicine.
Therein lies the problem.
Ryan Stewart retweeted
An essay worth reading, for every clinician and patient (with a PrCa paragraph)
The Quiet Half of Good Medicine jamanetwork.com/journals/jam…
Ryan Stewart retweeted
Earlier this year I was coding between cath lab cases - one hackathon later, I'm at Abridge. Now we're teaming up with Physician Side Gigs and @OpenAI to give physicians the same shot at HLTH. Bring a problem that bugs you every shift, and build it with top engineers from @AbridgeHQ and @OpenAI . Physicians only, no code needed, solo or with one colleague. Ideas due Oct 20. abridge.com/hlth2026
This but with the todotxt CLI todotxt.org/
How I get AI + my human assistant to do 50% of my work each day before I get out of bed:
I use Todoist to track my daily to-dos. Each task inside Todoist gets a description that follows a simple formula:
Why, Done, Access, Who
Why = the purpose of the task
Done = what does done look like
Access = what tools are needed to complete the task
Who = who is responsible for completion
Every morning Codex looks at Todoist at all the tasks due that day.
For any tasks where "Who" = Codex, it just completes the task.
This could be drafting follow ups, writing an email broadcast, scheduling a UPS pickup, or any number of other things.
For any task where "Who" = me or my assistant, Codex drafts a brief in the comments section of the task. The brief is designed to do as much of the task as Codex possibly can so that we can step in and finish it off.
The brief may add additional context, an exact phone number to call, a specific person I personally need to reach out to and the details of our last interaction, etc.
I highly recommend following the Why, Done, Access, Who context model for task management.
It's kinda a pain to add all those details for simple tasks like "book haircut" but 30 seconds of additional effort on your part enables your AI (or your human) assistant to take entire tasks off your plate in one shot.
Ryan Stewart retweeted
We built an all-synthetic simulation of a hospital that can be shared publicly without any issues. Our data quality is so high, physicians cannot tell the difference between real/synthetic patients. The data is fully verified -- perfect for RL.
Introducing Synthetic Hospital: an open, fully synthetic longitudinal EHR benchmark with verifiable ground truth!
1,268 patients, 5,602 encounters, zero PHI. Physicians could not reliably distinguish its charts from real ones.
📄 arxiv.org/abs/2609.30027
💻 github.com/sparkcpark/synthe…
✍️ sparkcpark.github.io/posts/f…
This is how I see Jev too. Obviously.
Replying to @willdepue
I see it as a point on the LLM pareto optimal curve in a regime that had a large revealed latent demand (no thinking, single token, low latency acceptable intelligence) that was under-invested into because of a race to higher intelligence.
Ryan Stewart retweeted
CancerBench: the frontier model cancer cure benchmark.
AI lab CEOs keep talking about curing cancer, so I made a benchmark.
One metric: how many types of cancer has your model cured?
All models are currently tied at zero.
It’s time to hillclimb!
cancerbench.com
Ryan Stewart retweeted
Once there was this kid who got into an accident and couldn't come to school. But when he finally came back, his hair had turned from black into bright white.
He said that it was from when the cars had smashed so hard.
Combine this with the new Epic plugin and you have what doctors call “running the list.”
During my commute:
“Today: 7 new patients, 4 post-op follow-ups, 2 pre-op counseling. Quality committee meeting at noon.
0830 — Ms. A, 63yo para 2 referred by Dr. Mitchell in Jonestown for urinary incontinence. PFDI-20 suggests mixed symptoms, stress-predominant. Already tried pelvic floor PT & oxybutynin, stopped for dry mouth. BMI 34, no prior surgery. Note is prepped. I sent your nurse two questions to clarify when she rooms her.”
@sama @OpenAI
Wonderful show from @imwithherband last night in Door County. This band is a national treasure. If you have an opportunity to see them, don’t pass it by. open.spotify.com/track/4z1dt…
Ryan Stewart retweeted
#SpecialContribution: We were eagerly expecting IUGA International Guidelines on OASIs. You can find them in @iuj_bluejournal:
link.springer.com/article/10…
#urogynecology #guidelines #iugaoffice
Ryan Stewart retweeted
Sunday question:
Is it morally right for a tax-exempt hospital to use tax-exempt capital to purchase a competing physician practice that pays taxes?
The hospital begins with a financial advantage provided by the public.
It uses that advantage to purchase the competitor.
The physicians become employees.
The independent practice disappears.
The hospital can now charge a higher price for the same physician performing the same service.
Who financed that acquisition?
What charitable purpose was served by eliminating the competitor?
Why should taxpayers subsidize the purchase of a business that was already serving patients?
And how many competitors may a charitable institution eliminate before it stops behaving charitably?





















