
medical doctor @uclms + engineer @uclcs // deployments @anteriorai (sequioa + NEA backed)
New York, USA
Joined September 2019
- Tweets475
- Following1.3K
- Followers485
- Likes2.5K
🤯
every company wants to build cloud-based autonomous agents for internal work and to power products. we built Claude Managed Agents as the API platform for building the most powerful AND the most secure agentic systems.
starting today, companies can host it themselves. we've iterated over the past year towards what we believe is the very best architecture for performance and safety. plus: agent identity for governance, otel for observability, and kill switches for peace of mind.
last but not least, for the first time, we are shipping a real evals product with self-hosted managed agents, so you can hillclimb to the consistently high quality outcomes you need your agents to achieve.
we've already got customers building systems to solve the world's hardest problems. bio research, chip design, and we're seeing people build serious software factories on this thing.
im really proud of this one. our team is so insanely focused on building the platform that makes it possible to leverage models to solve crazy problems safely and securely. this is a big step, and we can't wait to see what you build.
62
nyc marathon 2026
So I recently badgered my cinematographer @steveyedlin into making my ideal iPhone still camera app. It shoots RAW, bypasses the iPhone's look processing and instead uses the same image processing we use on our movies. apps.apple.com/app/apple-sto…
3
405
Kien Hang, MD retweeted
"Our technology keeps getting better. Our social lives keep getting smaller...
Everybody might prefer, in the abstract, a world of dinner parties, neighborhood friendships, and spontaneous gatherings. But on any given Wednesday at 7:45pm., it is easier to look at a screen than to host a party.
Modernity has shifted leisure from activities that require coordination with other people toward activities that can be consumed without the permission or participation of others. Compared to TikTok, a dinner party is a terrible leisure technology. It requires matching schedules, cleaning the house, buying food, accommodating children and allergies, tolerating awkwardness, and taking the risk that the evening is mediocre. By contrast, what does television ask of us? Nothing. TikTok? Even less.
We keep creating opportunities for downtime that eliminate the need for other people to be present."
derekthompson.org/p/the-deat…
Kien Hang, MD retweeted
some ideas for “muse for healthcare”:
- a morning digest pre-charting all patients for the day
- ambient monitoring for results (labs, imaging, etc) and notification of clinically actionable findings
- in-basket prioritization and triage
- auto-dialing other clinical sites to obtain records or other info
- monitoring of ED visits, admissions, or other specialist visits for a patient “watch list”
Kien Hang, MD retweeted
Guys it’s a misconception that Jev can’t hallucinate
It’s a non-generative LM ie it models probabilities of things given language as context
The guarantee is the type-safety, and that answers are deterministic - ie no stochastic sampling. The deterministic answers can still be confidently wrong!
It can still hallucinate if the training data on the topic was under cooked
Replying to @neural_avb
jev has immense applications in areas where hallucinations are fatal - like medicine
Kien Hang, MD retweeted
Riyan and I are excited to announce that we got accepted into a16z @speedrun.
At Sonder, we're building your digital twin.
We all know AI is here, yet only a few of us have really changed our workflows around it. I've tried and it is not easy. There's friction at every step & it still hasn't learnt to be me.
As the world learns to work with AI, your digital twin will make your experience smoother than mine.
We're hiring, reach out if you or someone you know is obsessed with on-device inference, teaching models how people work, or shaping how humans and AI work together.
You had to learn to use a computer. What if it learned to be you?
Introducing Sonder Labs, an applied AI lab building your digital twin.
Today, we’re excited to share that a16z @speedrun is backing us.
Our work starts with vision models small enough to live privately on your laptop - always on, seeing what you see. The more your twin learns about your workflows, priorities, and relationships, the less you have to explain.
And when it sees a way to help, it prompts you before you prompt it.
Ajit and I met deploying some of healthcare’s earliest LLM systems at Anterior. Working alongside nurses, we saw early what the rest of knowledge work is now confronting. There’s already more intelligence than we know how to use. We’re the bottleneck.
The tools we use capture what we produce, but lose much of what makes it ours: the iterations and rejected options behind the final result, the taste that defines what good looks like, and the intent behind our decisions. And the work doesn’t stay still. Priorities shift, workflows evolve, and exceptions become routine.
Your world can’t be described once. It has to be learned continuously.
Generic models are powerful, but they can pull work toward the average. We’re betting on AI that helps people become more themselves: sharper in taste, bolder in judgment, and more distinctive in how they work.
Thank you to @JoshLu for believing in our bet on open-weight models way back when it wasn’t obvious, and to @_CallMeMacy and @fromevanwang for keeping our feet on the ground and getting us in front of the right people.
Oh, and we’re hiring! If you or someone you know is obsessed with on-device inference, teaching models how people work, or shaping how humans and AI work together, message us.
Kien Hang, MD retweeted
This is one of the best engineering blogs you'll ever read.
Not *just* because you'll learn a lot, but because @vmg sprinkles in a bit of everything.
A great story. History of git infrastructure. Distributed systems. Benchmarks. All written by someone who can speak to every point from deep, personal experience.
It's also 5,300 words, so grab a drink and enjoy.
Kien Hang, MD retweeted
The breakthrough isn’t the median survival rate doubling, it’s the fact that they’ve finally managed to create a drug that can target the RAS(on) state, rather than selective KRAS mutations. This makes it the first multi selective RAS inhibitor that’s clinically proven to work. The implications are huge. KRAS mutations are found in:
1. 90% of pancreatic cancers
2. 40-50% of colorectal
3. 20-40% lung
4. 19-23% of ALL cancers
Cheers, chills, and a standing ovation when RASolute 302 showed unprecedented survival on daraxonrasib for patients with progressive pancreatic cancer
Seldom do you sense you’re witnessing a historic moment in cancer care but this feels like ras targeting has arrived
#ASCO26
Kien Hang, MD retweeted
A Polish cardiologist just beat 13,000+ developers at @anthropicai's global hackathon.
He built the app in 7 days, while literally working hospital shifts.
Here's the story of Dr Michał Nedoszytko (@mnedoszytko):
-born in Poland
-became a cardiologist, not a coder
-MD from Medical University of Gdańsk (2008)
-PhD in cardiovascular genetics
-moved to Brussels
-interventional cardiology
-the kind of doctor who threads catheters into hearts
-high stakes, zero margin for error
-but he had a side obsession
-software
-taught himself Laravel, Vue.js, Azure
-just continuously shipped until he gets better
-2026: Anthropic announces a hackathon
-13,000 applicants worldwide
-Michał has an idea
-patients leave doctors confused
-they forget 80% of what they're told
-diagnoses lost in translation
-what if AI could follow up?
-problem: he's a working cardiologist
-no sabbatical
-no "build week"
-so he codes everywhere
-hospital break rooms
-airport lounges
-on the plane to San Francisco
-7 days total
-PostVisit.ai is born
-upload visit transcript + medical records
-AI translates to plain language
-ongoing personalized guidance
-answers the questions patients are afraid to ask
-built by someone who sees confused patients daily
-result: 3rd place globally
-not a Stanford CS grad, not a YC founder, just a cardiologist who codes between saving lives
-why it worked:
-real problem, felt daily
-domain expert built it
-no hand-wavy demo
-actually works for actual patients
-privacy-first, GDPR compliant
-built with Claude, Codex, Gemini
The best founders aren't always going to in tech. The world is not ready for this shift.
Replying to @claudeai
🥉 postvisit.ai by Michal Nedoszytko
Patients leave doctor's offices every day without understanding their diagnosis.
Postvisit (built by a cardiologist) turns visit transcripts and medical records into ongoing, personalized health guidance.

































