Safe & regulatable AI/ML for health | My job is (mostly) error bars 🫡 (eg, conformal prediction) | CS PhD at Johns Hopkins. Prev at Yale. he/him
Joined December 2019
- Tweets 245
- Following 387
- Followers 387
- Likes 1,506
55 Photos and videos
Pinned Tweet
Apr 22
Can we ensure AI agents respect our safety constraints, even as they explore & improve?
- Medical LLMs that are helpful, & avoid false claims?
- Bioscience agents that generate effective molecule designs, & ensure they’re safe?
📄🧵w/ @samuel_stanton_ @clara_fannjiang @jiwoncpark @kchonyc @anqi_liu33 @suchisaria
Excited to share “Conformal Policy Control” ⬇️
1/12
1
25
70
22,454
Drew Prinster retweeted
accepted to ICML as a spotlight, see you in Seoul!
Apr 22
Can we ensure AI agents respect our safety constraints, even as they explore & improve?
- Medical LLMs that are helpful, & avoid false claims?
- Bioscience agents that generate effective molecule designs, & ensure they’re safe?
📄🧵w/ @samuel_stanton_ @clara_fannjiang @jiwoncpark @kchonyc @anqi_liu33 @suchisaria
Excited to share “Conformal Policy Control” ⬇️
1/12
1
7
68
10,967
Drew Prinster retweeted
Apr 30
Gina will be attending AISTAT presenting this paper. She is also close to graduating and looking for her next step. Talk to her there!
“Improving Coverage in Combined Prediction Sets with Weighted p-values” by @DrewPrinster, @suchisaria, @ChellappaProf, @anqi_liu33, & more proposes a framework for the weighted aggregation of prediction sets w/ weights assigned based on contribution: arxiv.org/abs/2505.11785 (6/7)
2
8
1,572
Drew Prinster retweeted
Apr 23
TL;DR: poster today at 3:15pm, P3-#1109!
Have you ever benchmarked your method on QM9, MD17, OC20, or ModelNet? It turns out that the 3D orientations of point clouds in commonly used datasets are highly non-random. How did we prove this and why should you care? 🧵
1
12
40
3,190
Drew Prinster retweeted
Apr 22
I took ~7 years off during undergrad. Worked at Starbucks, the postal service, a diner. Wasn't until making friends with some CS PhD students at UW Madison, who suggested sitting in on Eric Bach's class on the physics of computation, that I decided to go back (and then get a PhD)
Apr 22
I need more examples of people in academia who haven't had a linear path at all and missed years on the way to PhD and still did their PhD. I don't wanna feel all isolated here đź«©
16
230
3,950
216,522
Drew Prinster retweeted
Apr 22
You have a safe model you've tested, and you have a new post-trained model. How far can you trust a new model before it becomes unsafe? The answer goes to the heart of statistical decision-making. To be safe, the agent must be self-aware. Read @DrewPrinster's thread for more.
Apr 22
Can we ensure AI agents respect our safety constraints, even as they explore & improve?
- Medical LLMs that are helpful, & avoid false claims?
- Bioscience agents that generate effective molecule designs, & ensure they’re safe?
📄🧵w/ @samuel_stanton_ @clara_fannjiang @jiwoncpark @kchonyc @anqi_liu33 @suchisaria
Excited to share “Conformal Policy Control” ⬇️
1/12
4
15
3,757
Apr 22
Can we ensure AI agents respect our safety constraints, even as they explore & improve?
- Medical LLMs that are helpful, & avoid false claims?
- Bioscience agents that generate effective molecule designs, & ensure they’re safe?
📄🧵w/ @samuel_stanton_ @clara_fannjiang @jiwoncpark @kchonyc @anqi_liu33 @suchisaria
Excited to share “Conformal Policy Control” ⬇️
1/12
1
25
70
22,454
Apr 22
Safety and exploration, in this view, can complement rather than oppose each other. With the right balance they can encourage progress while avoiding pitfalls. This balance, however, must be determined from what we actually know, not from what we hope. It can be enough, it turns out, to know what is safe, and to know what we want to try next.
11/12
1
4
250
Apr 22
Many many thanks to the absolutely amazing team of collaborators on this project, who I was so privileged and lucky to work with! This couldn’t have happened without numerous and major contributions from @samuel_stanton_ @clara_fannjiang @jiwoncpark @kchonyc @anqi_liu33 @suchisaria
And, sincere thanks to support from Prescient Design @genentech, @HopkinsDSAI, and @MooreFound !
12/12
6
302
Drew Prinster retweeted
Feb 26
Introducing "DOTResize: Reducing LLM Width via Discrete Optimal Transport-based Neuron Merging" !
We introduce an optimal transport framework for Transformer width compression that redistributes signal across neurons rather than eliminating them 🚚⚖️
🧵 1/6
1
7
17
1,337
Drew Prinster retweeted
10 Dec 2025
we're hiring a Ph.D. intern! join us @genentech in South San Francisco for a summer advancing ML & statistical approaches for clinical trial design & analysis 📉💊DMs are open, feel free to reach out! 🔗tinyurl.com/yc3hfndp
1
31
170
29,058
Drew Prinster retweeted
4 Dec 2025
How can you evaluate agent trajectories with only black-box access to a verifier and the agent?
Introducing E-valuator: Reliable Agent Verifiers with Sequential Hypothesis Testing
❌no finetuning
❌no additional GPU compute
⬛black-box access
✔️controllable error rates w/ guarantees
Thread below:
2
7
28
5,442