Karandeep Singh
@kdpsingh.bsky.social
📤 4892
📥 729
📝 552
Faculty at UC San Diego.
#rstats
. Creator of Tidier.jl
#julialang
.
#GoBlue
. Views own.
reposted by
Karandeep Singh
Rohit Vashisht
about 13 hours ago
Aspired: Skill.MDPhD
0
2
1
reposted by
Karandeep Singh
Mattan S. Ben-Shachar
about 15 hours ago
Inspired: Skill.PhD
1
2
1
It sounds like Anthropic was right to be concerned.
add a skeleton here at some point
about 16 hours ago
0
3
0
Tired: Skill.MD Wired: Dr. Skill
about 16 hours ago
1
6
1
Is no one upset about the fact that they never sold birds in the first place?
1 day ago
0
3
1
Statisticians: “Data” is plural but “dataset” (a set of multiple data) is singular. Thank you for your attention to this matter.
2 days ago
0
10
3
reposted by
Karandeep Singh
Rohit Vashisht
3 days ago
House full on amazing panel discussion on Clinical Reasoning in the Era of AI at CDI2 conference at UCI
@kdpsingh.bsky.social
0
2
3
reposted by
Karandeep Singh
Rohit Vashisht
4 days ago
If you work with UC Health data or aspire to do so then it might be worth attending the CDI2 conference at UCI
na.eventscloud.com/website/5224...
loading . . .
Home
https://na.eventscloud.com/website/52244/home/
0
2
2
Schrodinger’s strait
5 days ago
0
11
1
Sales rep: The customer is always right. People: Wow… that’s such good advice. — AI: The customer is always right. People: This is a phenomenon unique to AI which we have dubbed “sycophancy.” We have no idea where AI got this from.
5 days ago
1
3
1
reposted by
Karandeep Singh
Jonathan
10 days ago
There's a third party Julia extension for Positron! It makes Julia a peer of R and Python in Positron.
open-vsx.org/extension/nt...
loading . . .
Open VSX Registry
https://open-vsx.org/extension/ntluong95/positron-julia
1
5
4
reposted by
Karandeep Singh
Rohit Vashisht
3 months ago
UC Health CDI2 upcoming conference! Thriving through change: Adapting, Advancing, Achieving Stellar listening of speakers, likes of which include
@kdpsingh.bsky.social
! Register 👇
na.eventscloud.com/website/5224...
loading . . .
Home
https://na.eventscloud.com/website/52244/home/
1
2
3
reposted by
Karandeep Singh
Den Delimarsky
8 days ago
Tiny personal news - I am now one of the Lead Maintainers for Model Context Protocol 👋 More work ahead, so if you have any feedback about the protocol, its docs, SDKs, or anything at all - let me know!
loading . . .
3
57
2
reposted by
Karandeep Singh
James Balamuta
11 days ago
Holy (native) Grail update: we cracked open the
#Shiny
temple and eight desktop apps tumbled out.
#rstats
,
#python
, native, containerized, shinylive, you name it. One
#Electron
shell, every runtime mode we could dream up, all from one R package. {shinyelectron}, coming soon to a desktop near you.
0
35
2
〽️
13 days ago
0
0
0
reposted by
Karandeep Singh
Jacobs Center for Health Innovation @UC San Diego Health
22 days ago
Health systems may have a blind spot if they aren’t thinking about AI consumer tool usage in caring for patients. New
@ai.nejm.org
editorial: When physicians use generative AI without institutional engagement, systems lose visibility and safeguards. Read ⤵️
ai.nejm.org/doi/full/10....
0
2
2
reposted by
Karandeep Singh
Nicola Rennie
21 days ago
🎉 ggauto is now on CRAN 🎉 An
#RStats
package that selects better chart types, and provides more accessible styling for
#ggplot2
plots 📊 Blog post explaining why I made it and how it works:
nrennie.rbind.io/blog/introdu...
#DataViz
loading . . .
Introducing ggauto: automating better charts – Nicola Rennie
The ggauto package is an opinionated ggplot2 extension package that aims to help people make better charts by default. This blog post explains why it exists and how it works.
https://nrennie.rbind.io/blog/introducing-ggauto/
7
194
64
Watching my kid manually type in references in a middle school essay because using a reference manager isn’t allowed. That is the most cursed thing ever.
21 days ago
4
8
0
reposted by
Karandeep Singh
UC San Diego Center for Healthcare Cybersecurity
22 days ago
Cyberattacks have halted care and disrupted devices across U.S. clinics. In a new piece,
@arpa-h.bsky.social
explains why it’s funding real-world cyber protections. Proud our CHC team built CRASHCART, restoring critical systems fast when ransomware hits. Read⬇️
arpa-h.gov/news-and-eve...
loading . . .
Modern Cyber Defenses: Resilient networks mean healthier patients and uninterrupted care
The Advanced Research Projects Agency for Health (ARPA-H) supports transformative research to drive biomedical and health breakthroughs ranging from molecular to societal to provide transformative hea...
https://arpa-h.gov/news-and-events/modern-cyber-defenses-resilient-networks-mean-healthier-patients-and-uninterrupted
0
3
2
Statistician: Hey, want a ride? ML researcher: Sure. *** hops in EV *** *** 5 minutes pass ** ML: What are you waiting for? Stats: Finishing up the power calculation.
26 days ago
0
3
0
reposted by
Karandeep Singh
Hadley Wickham
28 days ago
We have summer internships y'all! Come work at Posit on the PyData, tidymodels, shiny, or Connect teams:
grnh.se/tigz810a3us
. You will have an awesome time, learn a ton, and help advance our open source and pro tools 🧰
#rstats
#pydata
2
71
46
reposted by
Karandeep Singh
Stats and R
28 days ago
Neural networks that know what they don't know? 🤔 New post with Joshua Marie: fit Bayesian Neural Networks in R with {kindling} + {tidymodels} and get uncertainty estimates out of a familiar workflow. 👉
statsandr.com/blog/bayesian-neural-networks-in-tidymodels-with-kindling/
#rstats
#tidymodels
loading . . .
Bayesian Neural Networks in {tidymodels} with {kindling}
Showcasing the versatility of the `{kindling}` R package.
https://statsandr.com/blog/bayesian-neural-networks-in-tidymodels-with-kindling/
0
6
1
reposted by
Karandeep Singh
Posit
29 days ago
New in pointblank: Generate realistic, coherent synthetic datasets directly in
#Python
. 🛠️📊 Need test data that actually makes sense? Pointblank’s generate_dataset() ensures that names, emails, and locations stay consistent across rows, covering 100+ countries! Learn more:
posit.co/blog/buildin...
loading . . .
Building realistic fake datasets with Pointblank - Posit
With Pointblank, you can generate realistic, synthetic datasets by defining schemas with built-in coherence for geographic, personal, and business data.
https://posit.co/blog/building-realistic-fake-datasets-with-pointblank/
0
10
1
reposted by
Karandeep Singh
Laure Wynants
about 1 month ago
According to my pooled analysis, this joke is average [95% CI meh, 🤣]
add a skeleton here at some point
0
4
1
reposted by
Karandeep Singh
Cameron Patrick
about 1 month ago
I have a joke about multiple imputation, but it's not very good. I have a joke about multiple imputation, but it could be better. I have a joke about multiple imputation, but it's awesome. I have a joke about multiple imputation, but it's not funny. I have a joke about multiple imputation, but it's
add a skeleton here at some point
0
55
14
I have a joke about missing data, but
add a skeleton here at some point
about 1 month ago
0
31
5
the horror
about 1 month ago
0
2
1
reposted by
Karandeep Singh
Kevin Ushey
about 1 month ago
hmm, i need a sharpie. i better buy a pack of 50 from costco so this never ever happens again
0
9
1
reposted by
Karandeep Singh
Rob Hyndman
about 1 month ago
A new paper on anomaly detection:
robjhyndman.com/publications...
The methods are implemented in the weird
#rstats
package.
loading . . .
Anomaly detection using surprisals – Rob J Hyndman
https://robjhyndman.com/publications/surprisals.html
1
21
6
reposted by
Karandeep Singh
Coach Finstock
about 1 month ago
He's dissolving Ohio State University
add a skeleton here at some point
20
421
49
reposted by
Karandeep Singh
Hadley Wickham
about 1 month ago
These captchas just keep getting harder
#rstats
8
625
144
reposted by
Karandeep Singh
Simon P. Couch
about 1 month ago
Today we're releasing AI for RStudio. It's really, really good—I'd encourage you to point it at the messiest data sources you have and see what it can do.
www.simonpcouch.com/blog/2026-03...
7
115
36
kibbles vs. petfood.frames
about 1 month ago
2
8
2
reposted by
Karandeep Singh
Jumping Rivers
about 1 month ago
The recordings from Shiny in Production 2025 are now available. Talks from speakers around the world on how they use Shiny in R and Python to solve real-world data problems. Watch the sessions:
youtube.com/playlist?lis...
loading . . .
Shiny in Production 2025 - YouTube
Shiny in Production 2025 showcases real world lessons from teams deploying and maintaining Shiny applications at scale. Topics include infrastructure, DevOps...
https://youtube.com/playlist?list=PLbARZQfpqIKK9xAn0pOuYgd6cMl7Z04PW&si=Gu2Cqom9QywC2rcC
1
14
6
Appreciate the years of work by Andrew Wong, Yasir Tarabichi, Pat Lyons, and colleagues around the country to understand how routinely implemented predictive AI tools perform in diverse real-world clinical settings. Here’s a quick timeline...
add a skeleton here at some point
about 1 month ago
1
5
1
Tomorrow Night Bright or Catppucchin Mocha?
about 2 months ago
2
1
0
reposted by
Karandeep Singh
Alejandro Schuler
about 2 months ago
tibbles are fine, probably even good.
1
9
2
reposted by
Karandeep Singh
Dr Mircea Zloteanu 🌺🌞🍃
about 2 months ago
#statstab
#495 Unsure Calculator Thoughts: Nifty way to incorporate your uncertainty when making some calculations and decisions.
#uncertainty
#calculator
#unsure
#chance
#sensitivity
filiph.github.io/unsure/
loading . . .
Unsure Calculator
The Unsure Calculator is an online tool that lets you calculate with numbers you’re not sure about.
https://filiph.github.io/unsure/
0
23
9
reposted by
Karandeep Singh
James Balamuta
about 2 months ago
Small update on the python-on-iOS front: the unnamed notebook app now has a name -- Pyodios -- and a new trick. Swap between a local Pyodide kernel and a remote Jupyter backend mid-session. Want offline? Stay local. Want GPU? Call home. No drama either way.
#Python
#iosdev
#wasm
#Pyodide
#Jupyter
loading . . .
1
10
2
☑️
about 2 months ago
4
16
2
reposted by
Karandeep Singh
Julia M. Rohrer
about 2 months ago
Planning my next conversation starter
21
102
17
I love that whatever is going to happen will happen by 2030. Good to know.
add a skeleton here at some point
about 2 months ago
1
4
0
reposted by
Karandeep Singh
Bob Wachter
about 2 months ago
I enjoyed working with an all-star team – the great Lisa Rotenstein of UCSF and David Bates of Brigham & Womens – on this paper describing how to measure return on investment (ROI) for clinician-facing AI tools.
jamanetwork.com/journals/jam...
loading . . .
Measuring the Return on Investment for Clinician-Facing Artificial Intelligence Technologies
This Viewpoint discusses different ways to measure the return on investment on clinician-facing artificial intelligence tools as the technology advances.
https://jamanetwork.com/journals/jamainternalmedicine/fullarticle/2844893
0
6
2
reposted by
Karandeep Singh
Ambassador Frank Hull
3 months ago
🚨 kuzco is now on CRAN 🚨
cran.r-project.org/web/packages...
loading . . .
kuzco: Computer Vision with Large Language Models
Make computer vision tasks approachable in R by leveraging Large Language Models. Providing fine-tuned prompts, boilerplate functions, and input/output helpers for common computer vision workflows, su...
https://cran.r-project.org/web/packages/kuzco/index.html
6
16
9
reposted by
Karandeep Singh
Jacobs Center for Health Innovation @UC San Diego Health
about 2 months ago
We're hiring!
@ucsdhealth.bsky.social
& JCHI are looking for a Health AI Product Manager (Remote) to lead enterprise AI & digital health products, including Mission Control!
@kdpsingh.bsky.social
Apply & join us in shaping the future of health AI ⬇️
employment.ucsd.edu/health-ai-pr...
loading . . .
Health AI Product Manager - Remote - 138636
Health AI Product Manager - Remote - 138636 | Careers at UC San Diego
https://employment.ucsd.edu/health-ai-product-manager-remote-138636/job/FB43B227CC7B00CC0DB81620F8143D93
0
2
2
Instead of going to LLMs and agentic AI, I’m imagining an alternative world where we went from machine learning to machine talking and machine doing.
about 2 months ago
0
3
0
Tired: Logistic regression Wired: Pregenerative AI
about 2 months ago
1
10
2
reposted by
Karandeep Singh
Richard Riley (R²)
about 2 months ago
⭐ NEW VIDEO 🎬 : "The importance of sample size for the development & evaluation of AI-based prediction models for healthcare"
youtu.be/EN8NuKBS0W4
Training or evaluating prediction models for AI-based healthcare? This talk is for you!
loading . . .
Importance of sample size for AI-based prediction models in healthcare
YouTube video by Richard_D_Riley
https://youtu.be/EN8NuKBS0W4
2
11
4
reposted by
Karandeep Singh
Fabio Votta📊🐧
2 months ago
🚀 dashboardr is out! An
#rstats
package for building interactive dashboards with tidyverse-style syntax. Launched with a fun hackathon at
@ascor.bsky.social
(🍕 included). 📦:
favstats.github.io/dashboardr/
Big thanks to the dashboardr team, Digicomlab, and
@vivifabrien.bsky.social
for the logo 🎨
1
88
28
“linear in the log-odds space”
add a skeleton here at some point
about 2 months ago
1
26
2
Load more
feeds!
log in