iiinova — where your digital self keeps evolving

Joey Rudoler @jrudoler.bsky.social · 28/09/2026

iclr deadline was exhausting, but good neurips news was the motivation I needed to get over the finish line. excited to share what I've been working on recently -- tweeprint to come!

000

Joey Rudoler @jrudoler.bsky.social · 16/06/2026

@jordan.matelsky.com with jaw-dropping science and awe-inducing visuals. Come for the pretty pictures, stay for the insights about how neurons communicate!

121

Joey Rudoler @jrudoler.bsky.social · 04/11/2025

I've been using Affinity Designer for a few years now and really like it -- there's a learning curve but you really get full control. Seems like all the features + more are included in this free version! Super awesome for posters and making nice figures/graphics for papers or talks.

030

Joey Rudoler @jrudoler.bsky.social · 28/10/2025

In Philly, Philabundance is known for doing awesome work to fight food insecurity. philabundance.org If you have a PennKey you can double your donation by donating through the Penn's Way platform.

philabundance.org

Nonprofit Food Bank and Charity in Philadelphia | Leading the Fight Against Hunger

Our mission is to end hunger for good in the greater Philadelphia area. Learn about who we are, our initiatives and how you can help.

000

Joey Rudoler @jrudoler.bsky.social · 28/10/2025

With the government shutdown threatening SNAP and other benefits, reminder to academics to check if your university will match donations to food pantries and the like! e.g. @Penn is currently doubling donations to local charities through: pennsway.upenn.edu

pennsway.upenn.edu

Home | Penn's Way

120

Joey Rudoler @jrudoler.bsky.social · 22/10/2025

Excited be spending a few months at Tel Aviv University working on deep learning theory with Prof. Nadav Cohen and the Foundations of Deep Learning group. Amazingly collaborative group and department. Very much enjoying the cool science, time with family and friends, and outstanding food!

020

Joey Rudoler @jrudoler.bsky.social · 22/10/2025

Super nice results -- language features are represented in the brain (decodable from MEG) on a timescale that corresponds to how high-or-low level those features are (i.e. semantics are decodable for a long time, phonetics only briefly/locally)

020

Joey Rudoler @jrudoler.bsky.social · 07/09/2025

Special thanks to the organizers, incl. @eringrant.me @stefsm.bsky.social and @saxelab.bsky.social ! Great lectures and a fun interdisciplinary group 🙂

040

Joey Rudoler @jrudoler.bsky.social · 07/09/2025

Just spent two wonderful weeks in London for the Analytical Connectionism Summer School (hosted at Gatsby/UCL this year). Met lots of wonderful scientists at the intersection of cog neuro and machine learning. Learned a lot and can’t recommend more highly! Small meetings rule

191

Reposted by Joey Rudoler

Nathan Lambert @natolambert.bsky.social · 14/08/2025

I wanted to provide more color on this because its a bigger deal than the main Ai2 account is hyping it as. For example, the entire annual budget of the NSF for AI in 2026 is $655M dollars. To commit to a training models on single line item of about 20% of that is a huge deal.

4377

Reposted by Joey Rudoler

Jamie Cummins @jamiecummins.bsky.social · 23/06/2025

Social scientists should not use chat interfaces when using LLMs in their research: they are impressively inefficient, and obscure/impose important methodological decisions that require thought. THREAD🧵

37029

Joey Rudoler @jrudoler.bsky.social · 31/07/2025

Wrote a new, modern stats curriculum. Teach about probability and sampling via computational examples / simulations with real data. It's unbelievably helpful for intuition. Everything else follows. Online and open-source: jrudoler-teaching.github.io/understandin...

jrudoler-teaching.github.io

Lecture 00 – Understanding Uncertainty

052

Joey Rudoler @jrudoler.bsky.social · 16/07/2025

Check out my (open source) short course on introductory statistics and data science! It covers fundamentals of programming and probability, and then uses those to build up an intuition for hypothesis testing through sampling and simulation jrudoler-teaching.github.io/understandin...

jrudoler-teaching.github.io

understanding-uncertainty – Understanding Uncertainty

030

Joey Rudoler @jrudoler.bsky.social · 21/05/2025

I'm building a course from scratch this summer. Premise is that sampling / simulation are key for building intuition and statistical thinking. Students should learn permutation tests before they learn t-tests. Do folks agree?

120

Joey Rudoler @jrudoler.bsky.social · 21/05/2025

What's something you wish you learned in your first stats/data science course that would have helped you down the line? Like some key intuition or insight that crops up all the time in diverse problems? Something better than learning the formula for a t-test #MLSky #StatsSky

310

Reposted by Joey Rudoler

Community for Rigor @comm4rigor.bsky.social · 15/04/2025

Have you played with our Confirmation Bias Unit, yet? Head out to buff.ly/sa8UIeY and give it a try, share with your colleagues and students, and give us your feedback.

c4r.io

Community for Rigor | Units

We made a network of essential units to help you better understand the principles and practices of scientific rigor.

032

Joey Rudoler @jrudoler.bsky.social · 03/03/2025

There are two kinds of statisticians: those who like telling other people they're wrong, and those who don't talk at all

110

Reposted by Joey Rudoler

Yoshua Bengio @yoshuabengio.bsky.social · 29/01/2025

Today, we are publishing the first-ever International AI Safety Report, backed by 30 countries and the OECD, UN, and EU. It summarises the state of the science on AI capabilities and risks, and how to mitigate those risks. 🧵 Full Report: assets.publishing.service.gov.uk/media/679a0c... 1/21

7256104

Reposted by Joey Rudoler

Konrad Kording @kordinglab.bsky.social · 21/01/2025

Announcing a new week-long program for young computational neuroscience/ behavior professors to talk about rigorous science, mentoring, lab management, and networking in a stunning retreat setting. Do great science as a community and have fun doing so.

212255

Joey Rudoler @jrudoler.bsky.social · 20/01/2025

newly converted @weightsbiases.bsky.social fan here! honestly did not realize how much better it could be than tensorboard. just way more organized, pretty, intuitive, and feature-rich. shoutout once again to the awesome engineers building various MLOps tools for the rest of us to use <3

020

Joey Rudoler @jrudoler.bsky.social · 15/01/2025

And the company sells a pendant you can wear to bring the companion with you wherever you go... honestly feels dystopian. Does anyone have a more positive take on this? I feel like this has to be regulated...

000

Joey Rudoler @jrudoler.bsky.social · 15/01/2025

I have no chat history, no account, no data -- and this is the first message the bot sends!! Who does this help? Seems obviously like farming for engagement from users who want to commiserate and encouraging them to engage in negative thought patterns.

100

Joey Rudoler @jrudoler.bsky.social · 15/01/2025

I don't understand the product appeal of AI companions... and honestly the companies producing them sometimes feel predatory (though I believe some people have good intentions to reduce loneliness etc.) When I open friend.com the bot immediately turns on the anxiety / depression / alcoholism

200

Joey Rudoler @jrudoler.bsky.social · 13/01/2025

At Penn you can get a certificate for going to some extra training, but it seems pretty divorced from your effort/performance in the classroom. Departments could give teaching awards to the most highly rated TAs? Teaching *well* could be part of PhD degree-granting requirements?

000

Joey Rudoler @jrudoler.bsky.social · 13/01/2025

The reality is that this is what most researchers want — teaching is a chore and distracts from research. But it feels like a disservice to everyone and super out of whack with a university’s educational values.

100

Joey Rudoler @jrudoler.bsky.social · 13/01/2025

Not a new topic but what are effective ways to incentivize grad students to be better TAs? I really enjoy teaching but it seems there’s zero incentive to do a good job (beyond personal fulfillment and an altruistic desire to help students). We’re evaluated solely on research!

110

Joey Rudoler @jrudoler.bsky.social · 09/01/2025

Couldn’t agree more! I got on it ~2 weeks into grad school when I realized how fundamental those challenges are to the PhD experience. Wanted to invest preemptively. Also not true for every school, but student health insurance is pretty generous - my in-network copay is $10 per session. No brainer.

000

Reposted by Joey Rudoler

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 09/01/2025

If you’re in grad school, finding a therapist can be really helpful. The thing you’re doing is hard and it’s harder if you don’t have help managing imposter syndrome, stress, self esteem, and a whole bunch of other things.

56513

Reposted by Joey Rudoler

Sam Gershman @gershbrain.bsky.social · 07/01/2025

Key-value memory is an important concept in modern machine learning (e.g., transformers). Ila Fiete, Kazuki Irie, and I have written a paper showing how key-value memory provides a way of thinking about memory organization in the brain: arxiv.org/abs/2501.02950

arxiv.org

Key-value memory in the brain

Classical models of memory in psychology and neuroscience rely on similarity-based retrieval of stored patterns, where similarity is a function of retrieval cues and the stored patterns. While parsimo...

312331

Joey Rudoler @jrudoler.bsky.social · 23/12/2024

In the original tree-of-thought paper they just prompt an LLM to rate a candidate thought sequence or vote on the best one. Then they use these heuristics to search the tree with standard algos like BFS and DFS.

120

Joey Rudoler @jrudoler.bsky.social · 23/12/2024

Not clear to me if they're minimizing a different objective function at test time. if the "deliberative alignment" paper is any indication they may use an explicit reward model (there it's about safety compliance) to filter chains of thoughts to use in SFT. So still max joint probability of the seq?

210

Joey Rudoler @jrudoler.bsky.social · 23/12/2024

My absolute favorite content on the internet is this guy Adam Aleksic (@etymologynerd, but not on Bluesky) who posts about linguistics. Awesome combo of silly content (“I made a gorilla language”) and super insightful commentary about language and communication interacting with modern tech/society

youtube.com

RETURN TO MONKE 🦍 #conlang #linguistics #language

YouTube video by Etymology Nerd

110

Joey Rudoler @jrudoler.bsky.social · 20/12/2024

To be clear, this study doesn't in any way show that e.g. ChatGPT4o will get worse over time This study shows progress in the field (newer models improve on previous iterations), not "cognitive decline"

000

Joey Rudoler @jrudoler.bsky.social · 20/12/2024

Hold on, that's not at all what this shows -- they don't evaluate how a single model's performance changes over time, they just observe that newer models (trained on more data with newer and more advanced methods) are better than different, older models

100

Joey Rudoler @jrudoler.bsky.social · 20/12/2024

Visiting NYC really makes me feel like some sort of crunchy small town guy… but I live in Philly

170

Joey Rudoler @jrudoler.bsky.social · 15/12/2024

LLM research today would look so different without @hf.co... making models of scale and diversity so easily accessible to researchers is an amazing engineering feat. Such a catalyst for progress. 🙏

041

Joey Rudoler @jrudoler.bsky.social · 15/12/2024

Agreed - curating them is expensive though. How do we incentivize orgs that have the data (or have access to the data) to do it? In research, my sense it that the incentive for curating these benchmarks is that they allow researchers to claim "my model is SOTA on X" which gets published

010

Joey Rudoler @jrudoler.bsky.social · 12/12/2024

I absolutely love Keynote for academic presentations Built-in support for Latex equations, easy UI, presenter view, super-customizable templates, looks beautiful, has great recording features Is it just the collaborative editing that has people using google slides or beamer/overleaf?

210

Joey Rudoler @jrudoler.bsky.social · 06/12/2024

Shoutout to the guy on my flight playing 2048. Forgot it existed and am now immediately hooked again

020

Joey Rudoler @jrudoler.bsky.social · 03/12/2024

Go follow @yuh42.bsky.social ! She’s brilliant and has great insight into the theoretical side of transformers, in-context learning, and diffusion models. Constantly amazed by her and many other students in our cohort + department

110

Joey Rudoler @jrudoler.bsky.social · 02/12/2024

Love seeing all the recent progress on neuro foundation models!! Super important for the field to build more robust models that leverage data across subjects and tasks…. Needing to retrain subject and task-specific models from scratch just makes the research too expensive!

011

Joey Rudoler @jrudoler.bsky.social · 02/12/2024

Would love to be added! But much more importantly you need @tomdonoghue.bsky.social on here for sure 💪

000

Reposted by Joey Rudoler

Federico Adolfi @fedeadolfi.bsky.social · 30/11/2024

Are we really giving up on simplicity and elegance and adding hundreds of terms to our objective functions?? Because that would be a huge loss

1293

Joey Rudoler @jrudoler.bsky.social · 29/11/2024

I think it's funny that for the past week I haven't been able to stop listening to: 1) the Wicked movie soundtrack 2) the new Kendrick Lamar album Good luck to the AI trying to learn my music preferences...

140

Joey Rudoler @jrudoler.bsky.social · 28/11/2024

Yeah I just think it seems sort of defensive - my read is that some writers / content creators feel threatened by AI and feel a need to discredit it entirely What’s weird is that this is fighting a narrative that I don’t think really exists (“AI can replace journalists” - few people believe this)

270