Seth Hain

Contemplations on computation, cognition, chords, and care....
Expressly individual insights

[Seth Hain @sethHain]

@Yale Find more on Curiosity here: https://t.co/1zEPCKWbUk"

[Seth Hain @sethHain]

Researchers at @Yale using Curiosity—Epic's generative medical event model, which simulates a patient's likely future course from their record — looked at adults discharged from the ED with abdominal pain, one of the most common and most uncertain presentations in emergency medicine. Traditional risk models answer a binary question: will this patient come back? Curiosity answers a richer one: if they return, when, and will that return end in discharge or admission?

Two patients can carry the same overall revisit probability but face very different paths—one headed toward a quick outpatient follow-up, another toward an early admission. A binary score flattens that difference. A trajectory surfaces it.

A single pretrained model, like Curiosity, can generate calibrated predictions across many outcomes without retraining. As a result, the focus and time shift away from building a bespoke model for every clinical question and toward deciding which questions are worth asking. The team moved from idea to results in a matter of weeks.

It also highlights an emerging skillset: clinicians who pair deep clinical reasoning with real fluency in generative AI. The questions they choose to ask are the key ingredient.

Preprint here: https://t.co/bvQJ1c5JK0

[Epic @HeyEpic]

How does 5 years of data sound?

BMI and GLP-1 trends are now available on the Epic Research Data Tracker:

[Seth Hain @sethHain]

Longtime listener; first time caller. Had a blast exploring a wide range of topics - from scaling laws to Paperboy (the Nintendo game) - with @arjunmanrai and @AndrewLBeam .

[NEJM AI @NEJM_AI]

In the latest episode of AI Grand Rounds, @sethHain, senior VP of R&D at Epic (@HeyEpic), describes how his company is building foundation models that respect institutional autonomy, minimize burden, and prioritize safety. Full episode: https://t.co/8bURhrMXna

[Seth Hain @sethHain]

https://t.co/sOlSt8IUr2

[Jack Clark @jackclarkSF]

https://t.co/LmpEfSs06w

[Seth Hain @sethHain]

Imagining a thoughtfully curated, hard-bound book (a la @stripepress) collecting the essential essays and papers demonstrating how society dealt with this moment in AI. Trying to compile what truly deserves to make the cut.

[Seth Hain @sethHain]

Framing to consider for the year(s) to come:

https://t.co/OolorNpuHF

[Ivan Zhao @ivanhzhao]

https://t.co/fxHYR6S29D

[Seth Hain @sethHain]

@wiley_ladd Go Cornhuskers!

[Seth Hain @sethHain]

Health systems are leading the way on AI research and adoption. It was an honor to share their real-world results with the tech community at #MSIgnite.

The speed and scale of what’s happening in healthcare right now is remarkable. And what’s coming next is even more exciting.

[Epic @HeyEpic]

At Epic, we create technology to help people get and stay well.

AI is embedded throughout our applications—from the clinic, to the bedside, to the back office.

Worldwide, hundreds of thousands of clinicians are using it to improve care.

Here it is in action at #MSIgnite:🧵

[Ladd Wiley @wiley_ladd]

US News Best Leaders 2025: Judy Faulkner - “You predict the future for two reasons,” Faulkner says. “One is to prepare for it. And two is to change it.” https://t.co/JImY3y3KlK

[Epic @HeyEpic]

At @ChristHospital, 141 people started treatment earlier because Epic’s AI helped spot lung cancer in early stages.

Here's Mark's story:

[Seth Hain @sethHain]

Geniunely enjoy ever conversation I get to have with @mattlungrenMD and @JustinNordenMD - including this one we decided to record.

https://t.co/CZjNidAb1V

[Epic @HeyEpic]

https://t.co/uWmW8HC1j2

[Seth Hain @sethHain]

@emollick What we may learn if this same mystery and the potential "law-like" structures apply to the Comet models (transformers trained on sequences of medical events) has been a key inspiration for us at @HeyEpic as well.
https://t.co/lZfKUTCdrG

[Ethan Mollick @emollick]

We really have not made a lot of progress on explaining the deep mystery of LLMs:

How does a model using matrix multiplication to predict the next word manage to simulate human thought well enough to do all the very human-like things it does? And what does that mean about us?

[Zachary Charles @MatharyCharles]

Cool new paper out of Epic that trains foundation models + derives scaling laws for generative medical event modeling.

Interestingly enough - they find that the Chinchilla scaling parameters basically hold in this setting as well!

🧵some observations and questions below

[Rick Berke @rickberke]

He was 21 when he programmed MyChart. Now he’s the president of Epic https://t.co/15IAOqf7qX via @statnews @brittanytrang

[Seth Hain @sethHain]

☄️☄️☄️ Pleased to share our latest research on creating personalized medicine at scale by combining Epic Cosmos and generative AI.

We created CoMET, a decoder‑only transformer that generates next medical events to simulate patient trajectories. Trained on 115B medical events from Epic Cosmos; evaluated on 78 real-world tasks spanning diagnosis prediction, disease prognosis, and healthcare operations; established scaling laws on medical event transformers; and, importantly, determined that clinical performance improves along with scaling.

Grateful to both the Epic Cosmos community for making this possible and the collaboration across @Yale, @MSFTResearch, and @HeyEpic.

#ugm2025

https://t.co/x1MTkemvr3

[Seth Hain @sethHain]

☄️ ☄️ ☄️

[Seth Hain @sethHain]

Excellent, generally applicable framing by @benthompson

[Seth Hain @sethHain]

@nayafia managed to weave together everything from meditation to org structure to network theory in a highly anti-antimemetic way.