
Space Cowboy! Researcher with @Space_Station and Third Year Med Student @DukeMedSchool Now an AI Masters Student
NASA’s Secret Lunar Base
Joined November 2014
- Tweets849
- Following158
- Followers333
- Likes4.2K
Pinned Tweet
Two areas of interest for me AI in Medicine and Space Medicine, you wouldn’t know it but Interventional Radiology is basically the only field for me.
3
3
289
Dominic Tanzillo retweeted
BREAKING: NASA makes U.S. history with first-ever quantum link established between an aircraft & the ground.
Dominic Tanzillo retweeted
Today marks 26 years of continuous human presence in space — meaning an entire generation has never known a day without people living above Earth. That’s pretty special.
In my course on space medicine the last lecture is “Do you have what it takes to be an astronaut?”
When we published it in 2021, the number one response for kids in China was astronaut. In America it was YouTuber.
Let’s win it back!
1
59
Watched an undergrad at the coffee shop feed his entire problem set into ChatGPT.
Have some dignity. Do it at home, behind a VPN, with the lights off, like the rest of us.
48
Dominic Tanzillo retweeted
The future of #ArtificialIntelligence is not pre-determined. As a technology developed by human beings, its future depends on the choices we make. We therefore have the responsibility to guide, change and, when necessary, reject its applications. A reliable system that serves the human person is of greater value than one that is exceptionally powerful but whose consequences cannot be adequately foreseen or controlled.
Now that the AI-in-math conversation has shifted from “should this be allowed” to “how do we adapt,” I’m curious whether the field gets more or less open to outsiders. Does a Lean proof from someone outside math academia now invite more scrutiny, or less?
If you want it to double as a collaboration ask:
Math has long been unusually open to outsiders with good proofs. I wonder if AI changes that. Selfishly asking: I have ideas about the math behind test ordering and diagnosis in medicine but not the training to formalize them. Is the door still open for collaborations like that?
80
I just got paid by @XMoney. This has me interested in post more science and education content here. Feels like early days of YouTube again.
38
Why does every "Harry Potter adult" identify as a Ravenclaw or Hufflepuff?
Was everyone else just at football practice and parties?
1
49
This image is getting a lot of traction, so I want to add the male medical student's perspective on the OB/GYN rotation.
I had a great rotation, and I also had plenty of patients decline to have a student in the room. It usually went like this: the attending or resident asked if a student could join, the patient asked whether the student was a man or a woman, and when they heard “man,” roughly 30-70% (depending on the day) declined. Some were fine with me taking the history but not with me being there for the exam. One patient told me she actually preferred male clinicians because she found them more careful. It varies, and it depends on the patient in front of you.
Rather than sulk, I would always offer to start the note while the resident did the exam, or to take on chart review and med rec. For many women, the OB/GYN office is where they get their primary care. That's one reason the replies saying the rotation should be optional miss the mark. OB/GYN is 10 to 20% of Step 2 CK, and it's one of the best places to practice primary care.
A few tips, especially for male students:
Early in the rotation, a male resident sat me down and walked me through how he performs every pelvic exam. He was candid that it's harder for him than for his female colleagues because the exam is so sensitive. His advice was to narrate everything, tell the patient what's coming before each step, and say some version of, “If at any point you want me to pause or stop, just tell me. You're in control.”
A week later, after a colposcopy and pelvic exam, the supervising NP told me it was one of the best exams she'd seen from a student, and she put that in my evaluation. I mention it only because the advice works.
On L&D and urogynecology, I introduced myself to every patient and their family before surgery as part of the team. The attendings then asked whether it was OK for me to take part in the exam and the procedure. Only one patient declined, which freed me up to chart, review other cases, and study for my shelf.
Even though I came in having delivered babies as an EMT in rural, out-of-hospital settings, many families were fine with me watching but not with me taking part in the delivery. That's fine too. Often my job was to explain to the family what was happening in the room while the residents and attendings were busy. Once, that meant catching a first-time dad as he fainted.
The broader point for anyone starting rotations: treat everyone as part of the care team, including the patient. That turns the rotation into working together for the patient's health rather than something a student is owed. When a patient says no, that's informed consent working as it should, not something to lament.
LMFAO
Readers added context they thought people might want to know
Misleading
Post intentionally crops out the caption where the OP states:
"And I couldn't be more okay with it. The absolute number one most important thing in medicine is, and will always be, the patient"
x.com/ZiZiGee_127/st…
1
255
Posts like this have people worried about A.I. displacement in healthcare. Right now US Healthcare is tilted mostly at catching disease and not about optimizing health and wellness. There are many reasons for this least of which is the cost / benefit analysis every doctor runs.
>be me
>feel like shit
>go see the doctor
>doctor: "your labs are normal"
>me: "sir, what does normal mean?"
>doctor: "average for your age"
>me: "the average person also feels like shit, sir"
>doctor has no rebuttal
>absolutely refuse to accept this
>start measuring everything
>sleep, HRV, glucose, grip strength, resting heart rate, biological age via 3 different clocks, everything
>doctor asks why I'm back so soon
>show him 40 tabs of my own bloodwork
>he says "this is a lot"
>I say "you had 12 years of med school and less data on me than a Twitter account with 9 followers"
>he does not respond to this
>go home anyway
>message the guy with 9 followers
>he does not have a medical degree
>he has better data than my doctor did
>I trust him now
>my doctor still has my copay
>this is fine
1
69
Instead, doctors are incentivized to find a diagnosis and treat it. Catching frank deteriorations in health rather than help people live and feel better.
1
8
Dominic Tanzillo retweeted
The most meaningful moments of my NASA career did not take place in space. They were supporting astronauts and their families through missions, and mentoring interns and new hires as they began their own journeys in technical and public service.
Service is ultimately about people, all people.
I’m excited to share that I have joined my alma mater, Cal Poly, focused on strategic initiatives, partnerships and philanthropy.
As I retire from the U.S. Navy and transition to NASA astronaut emeritus, I’m grateful to continue serving NASA while beginning this new chapter at Cal Poly.
I look forward to helping create more opportunities for the next generation of STEM, faith, and service leaders through Cal Poly’s Learn by Doing education.
Dionna and I are excited to come back to San Luis Obispo, where we met 30 years go this month, and join the Mustang community. #CalPolyProud
NASA Names Two Artemis II Astronauts to Emeritus Program nasa.gov/news-release/nasa-n… via @NASA
Dominic Tanzillo retweeted
We have found stable singularity on 3D Euler!
anima-ai.org/2026/09/07/stab…
Our starting point is a physics-informed neural network (PINN) to come up with an approximate answer, and then to argue stability around that to complete the proof.
The challenge so far has been that PINNs have not been successful in discovering singularities on the current problem. A common failure mode is PINNs converging to a trivial solution. We take special care to nudge our PINN to interesting regions through a combination of constraints, and we believe this is a novel way of making PINNs work for such hard optimization problems.
We also carry out a detailed study of the transport field of our approximate profile, and show it has promising properties of local outgoing flow, essential for proving linear damping, which is an important ingredient of overall stability.
We believe that such physics-informed and physics-centric AI are critical ingredients across many areas of research involving physical systems, and LLMs lack such physical grounding.
We have been working on this problem for much of this year, and we just saw the announcement by Tristan on Euler with forcing. In contrast, we consider without forcing and use a PINN formulation. @Caltech
Dominic Tanzillo retweeted
Frame the second reason. Hang it in the Louvre.
GODFATHER OF AI ADMITS HE WAS WRONG ABOUT RADIOLOGISTS
geoffrey hinton predicted in 2016 that within about 5 years radiologists wouldnt be reading scans anymore
10 years later he gives two reasons he got it wrong
first, making scans cheaper and faster didnt mean hospitals suddenly needed fewer radiologists. it meant they could just do more scans
and second, he admits he didnt really understand the job itself
his picture of a radiologist came mostly from one former student who spent his time reading scans and barely talking to people
the AI part actually went pretty close to plan. machines got really good at reading scans
but making one part of a job cheaper doesnt automatically make the whole job disappear
AI can shrink a task without shrinking the job















