@kdpsingh.bsky.social focusing on the "build before you buy" mentality. A lot of the AI tools that are most useful to clinicians aren't actually commercially available, so internal teams build tools they need, like their NoteReader which can help automate measurements. #AMIA2025 #MLSky #MedSky

RNG state management need to be a whole lecture in it self, may be two.

“It is simpler to do erroneous things.” - @f2harrell.bsky.social H/t @phdemetri.bsky.social stats.stackexchange.com/questions/67...

One of the fun things about launching @timead.bsky.social is the amazing early career folks. We started a "scientist spotlight" website section. The 3 posted are just our first few - really gratifying to see the work of Master's & PhD students, and post-docs -more spotlights coming! bit.ly/3VCa84g

Love writing math? Tex is the only way :-) Try @typst.app if you haven’t allready.

I wrote a LinkedIn post on advice for incoming Master's students in public health and epidemiology. tl;dr: do hard things, get help when needed, make friends and thank people, and have fun - it's amazing. #EpiSky #DataSciSky #PublicHealth #GradSchool Full article: bit.ly/4neVYlE

Tired: Global interpreter lock for data heavy parallel processing in Python Wired: Reading data in 1GB chunks and processing sequentially

Data fog is a new one! @caltrain.com station, SF.

We love to see JCHI's @kdpsingh.bsky.social, @ucsdhealth.bsky.social named one of 24 new ACMI Fellows! His leadership in health AI, model governance & informatics policy is reshaping how AI is used responsibly in care. Read more⤵️ amia.org/news-publica...

From Clinician to Chief Health AI Officer: A Conversation with @kdpsingh.bsky.social www.podbean.com/ew/pb-9t5e4-... For clinicians, Singh’s story is a reminder that the best AI is guided by patient care, deep expertise, and humility about the limits of technology. Inspiring!

Late night LLM training thoughts: I’m increasingly appreciating APEs over other position embedding. Their simplicity makes them easy to implement and efficient in distributed training setups. APEs could also provide a stable foundation for enhancing the consistency of LLMs.

qwen is good, like really good!

Statistician: What is zero-shot learning? ML researcher: It’s when you don’t train your model, you just use it. Stats: So you just take a shot? ML: Exactly. Stats: One shot… ML: Exactly. Stats: … ML: Makes sense tho. Think of it like Python list indexing, where the first shot is the zeroeth.

Manuscript review requests are like poking one bee and getting the whole dang hive buzzing after you! Say yes to one, and suddenly you’re swarmed with a zillion more “review this, please!” emails.

Mother: I have twins. Doctor: Oh, so they were born on the same day? Mother: No, they were born with the same propensity score.

Tired: Adjusting for covariates Wired: “Building a digital twin”

If you understand the nullspace, you understand the matrix! — Gilbert Strang

“Our model is probably in our view the best model for this task and the fastest and second cheapest but not the best performing but the benchmarks don’t reflect the nuances of real-world use” is a whole lot of words to say that it’s not SOTA.

Tired: Long context length Wired: No context length

The more I learn about @duckdb.org the more amazed I get, and more I realize how much I don’t really know, and a long way to go!

Streamline data app development in Positron with the App Preview feature. 🪟 No more context-switching! Now you can run & debug your #RStats and #Python data apps (Shiny, Streamlit, Dash, etc.) right inside Positron's integrated Viewer pane. Learn more: positron.posit.co/develop-data...

Thanks Costco!

Is outlook down? Or just me!

At this point, the statisticians might even settle for a physician doing the statistics rather than this nonsense.

Positron’s integrated color picker is super handy for tweaking colors directly in your code!

Data to Decisions: Engineering the Foundations for Target Trial Emulation and Causal Inference in Medicine Across @uofcahealth.bsky.social Excited for this talk at UCSF-Epibiostat. I will discuss our ongoing efforts in harnessing large-scale RWD for post-market monitoring of therapeutic.

The catch in catching cancer early! As usual an impeccable article by Siddhartha Mukherjee in @newyorker.com All the more important when one tends to think deeply about causal inference from healthcare data! A must read. www.newyorker.com/magazine/202...

Swimming in DuckLake! @duckdb.org

L3M: Large language life models L2M: Large language models

Appreciated the opportunity to partner with Aaron Boussina to share our experience at UC San Diego Health in using LLMs to measure quality, safety, and patient flow through our health system at the National Academy of Medicine Leadership Consortium. You can’t improve what you can’t measure.

DuckDB is straight-up fire!

One of those rare and remarkably beautiful studies, often published once in long time. Read with evening chai to enjoy this beautiful work! The mechanics behind the beauty of roses | Science www.science.org/doi/10.1126/...

NotebookLM now supports Punjabi. support.google.com/notebooklm/a...

Great meeting everyone!

Excited for this seminar!

The K2-18b paper is now up as a preprint (to be followed by the final paper soon) arxiv.org/abs/2504.12267

Are you in SoCal? Come join me on April 24 for a behind-the-scenes talk on the origin of Tidier.jl for #julialang, and why #rstats users should give it a look. More details will be posted here: www.meetup.com/socal-rug/

Congratulations, one and only @kdpsingh.bsky.social www.statnews.com/status-list/...

Llama 4 series is here ai.meta.com Incredible progress!

Legitmately thrilled to share our latest work, in which @fernpizza.bsky.social solved an experimental challenge in plasmid biology as old as the field: measuring how plasmids compete and evolve within individual cells!

Intrinsically disordered regions as facilitators of the transcription factor target search https://www.nature.com/articles/s41576-025-00816-3 (read free: https://rdcu.be/eaMBK)

What an incredible work, and joyful read! Disease diagnostics using machine learning of B cell and T cell receptor sequences | Science www.science.org/doi/10.1126/... @anshulkundaje.bsky.social and team.

The capabilities of the large language of life models (LLLMs) are rapidly proliferating! nature.com/articles/d41... @nature.com arcinstitute.org/manuscripts/... @arcinstitute.org science.org/doi/10.1126/... @science.org

I am excited to partner with our AI researchers in cancer care at @ucsdhealth.bsky.social @ucsdhealthsci.bsky.social to ensure that we can bring cancer discoveries to the bedside. Learn about the great work happening at Moores Cancer Center: view.publitas.com/77e2eb4e-53b...

Dr. @emilyalsentzer.bsky.social, a Stanford faculty member and expert in clinical #AI, discusses the evolution of natural language processing, the challenges of AI in clinical settings, and what the future holds for open-source medical AI. Full episode: nejm.ai/4gOGeSo #MedSky #MLSky

“Researched models aren’t implemented. Implemented models aren’t researched.” Karandeep Singh, Chief Health AI Officer @ucsdhealth.bsky.social & associate prof @jchi-ucsd.bsky.social, closes out the keynote session by discussing the health AI paradox. @kdpsingh.bsky.social #SPIEMedicalImaging

This is amazing work, I have no words!! This is inspiring and this is the goal !!! www.science.org/doi/10.1126/...

Very thankful of @atulbutte.bsky.social for a push to learn SQL very early on years ago. Development like these in incredible tools like @duckdb.org saves tons of time, disk and memory, and makes one really feel like 🏄 on large volume of data!

If someone can make a DeepSikh R1, I will gladly use it to help teach Punjabi class.