Sign in

Leif Sieben

@leif7ieben.bsky.social
342 followers 1.4K following 57 posts

Master student @ ETH Zurich Visiting Student @ MIT and Broad Institute Working on machine learning for drug discovery and bringing all of chemistry into the age of big data and AI

PostsRepliesMedia
Leif Sieben @leif7ieben.bsky.social · 08/03/2026
The biggest bottle-neck to my personal code productivity: The fact that OpenAI still hasn't pushed a Codex mobile app.
0130
Leif Sieben @leif7ieben.bsky.social · 29/12/2025
My paper of the year is Andrew Gordon Wilson's "Deep Learning is Not So Mysterious or Different". I'll be thinking this year about what family of functions (support) combined with what prior over parameters (inductive bias) can actually well capture drug discovery data including activity cliffs.
0120
Leif Sieben @leif7ieben.bsky.social · 26/10/2025
You learn a lot about the underlying system design of your apps when you run them in a low data environment.
000
Reposted by Leif Sieben
Elizabeth Wood, PhD @lizbwood.bsky.social · 22/09/2025
A fundamental lesson of modern AI is that scale is essential: training bigger models on bigger datasets unlocks new capabilities. A fundamental lesson of AI engineering is that scaling up isn't trivial: it is not just a matter of spending more money and resources.
173
Leif Sieben @leif7ieben.bsky.social · 07/09/2025
Strong Platonic Representation Hypothesis: the universal latent structure of text representations not only exists, but can be learned and, furthermore, harnessed to translate representations from one space to another without any paired data or encoders.
110
Leif Sieben @leif7ieben.bsky.social · 03/08/2025
Got recommend this substack from Leash bio by a friend. I think this is a masterclass in how to correctly split the data if there ever was one. Respect your chemistry folks! open.substack.com/pub/leashbio...
open.substack.com
Data contamination is all random forest needs
Here's why we believe our Hermes prediction results are real
000
Reposted by Leif Sieben
Simon Fisher @profsimonfisher.bsky.social · 28/07/2025
Not sure who came up with "Manhattan Plot", but in 2014 I coined the alternative term "Nijmegen Plot" (inspired by the Dutch town where I live) to describe underwhelming results from our earliest genome-wide association scans of language/reading traits.
Contrasting photographs of the night-time skylines of Manhattan (left) and Nijmegen (right), with matching genome-wide association plots underneath each.
210921
Reposted by Leif Sieben
Alex Selby-Boothroyd @alexselbyb.bsky.social · 28/07/2025
Love these maps of "street-text sightings" in the Pudding's latest piece pudding.cool/2025/07/stre...
0239
Reposted by Leif Sieben
Sander Dieleman @sedielem.bsky.social · 28/07/2025
Great blog post on rotary position embeddings (RoPE) in more than one dimension, with interactive visualisations, a bunch of experimental results, and code!
jerryxio.ng
On N-dimensional Rotary Positional Embeddings
An exploration of N-dimensional rotary positional embeddings (RoPE) for vision transformers.
0192
Reposted by Leif Sieben
Keyon Vafa @keyonv.bsky.social · 14/07/2025
Can an AI model predict perfectly and still have a terrible world model? What would that even mean? Our new ICML paper (poster tomorrow!) formalizes these questions. One result tells the story: A transformer trained on 10M solar systems nails planetary orbits. But it botches gravitational laws 🧵
24114
Reposted by Leif Sieben
Greg Landrum @greglandrum.bsky.social · 17/07/2025
Today's #RDKit blog post is a heartfelt plea for clearer communication. greglandrum.github.io/rdkit-blog/p...
greglandrum.github.io
Please stop saying “The Tanimoto similarity is” – RDKit blog
A simple tip to explain what you actually did
2316
Reposted by Leif Sieben
Mark Riedl @markriedl.bsky.social · 13/07/2025
There is a new startup from China called Moonshot. The original “moonshot” was the Apollo Program. An AI based moonshot could be referred to as an “AI pollo” program. “ai pollo” in Italian means something like “to the chicken”.
2101
Leif Sieben @leif7ieben.bsky.social · 26/06/2025
I was recently on a flight with free Wi-Fi for texting but nothing else. Jokes on them: I can use Llama through WhatsApp now …
000
Reposted by Leif Sieben
Greg Landrum @greglandrum.bsky.social · 20/06/2025
The new #RDKit blog post, inspired by a question from @valencekjell.com, looks at the impact of molecular size on similarity thresholds. greglandrum.github.io/rdkit-blog/p...
greglandrum.github.io
The impact of molecular size on similarity. – RDKit blog
An exploration of how molecular size influences fingerprint similarity.
3115
Reposted by Leif Sieben
Pierpaolo Morgante (He/His) @piermorgante.bsky.social · 04/06/2025
Yay for @pschwllr.bsky.social and @mlederbauer.bsky.social (and all your co-authors who aren't on BlueSky yet) 🥳 This #dataset is a prime example of #GoodData, and it ties nicely with what @clarakirkvold.bsky.social and @grynova.bsky.social were talking about a few weeks ago in their #JournalClub
062
Reposted by Leif Sieben
Teddy Zartler @quantumtessera.bsky.social · 13/06/2025
I've got a joke about Osysseus. I got lost on the way to the punchline...
011
Reposted by Leif Sieben
depths of wikipedia @depthsofwikipedia.bsky.social · 13/06/2025
smell rights. in the US, Hasbro has a tradmark for the smell of Play Doh.
872106194
Reposted by Leif Sieben
Leif Sieben @leif7ieben.bsky.social · 05/06/2025
change my mind: bruot RIS to Bibtex converter is the best website ever built. www.bruot.org/ris2bib/
bruot.org
Online RIS to BibTeX converter
The simple RIS (EndNote) to bib (BibTeX) online conversion app.
001
Leif Sieben @leif7ieben.bsky.social · 09/06/2025
If anybody out there working on antimicrobial resistance (AMR) and needs some motivation on this gloomy New England Monday.
000
Leif Sieben @leif7ieben.bsky.social · 07/06/2025
I think the ranking of things which are hard to predict goes: 1. The stock market. 2. LaTeX figure placement. 3. The meaning of life.
010
Reposted by Leif Sieben
Bookshelfie ⭐️ @bookshelfie.bsky.social · 06/06/2025
#booksky
374189793205
Reposted by Leif Sieben
Maarten Dobbelaere @maartendobbelaere.bsky.social · 06/06/2025
Cheminformatics family businesses be like
041
Leif Sieben @leif7ieben.bsky.social · 06/06/2025
One of the surprising things about working in a microbiology lab is that you become more worried about washing your hands before using the restroom rather than after.
100
Reposted by Leif Sieben
shri @shrikhalpada.dev · 04/06/2025
I think the thing I'm most excited to see over the next ~10 years of #dataviz is web-based content that interweaves long-form text and modular interactives. Not as heavy as scrollytelling and not as aimless as a dashboard, but something in between. This is what I was going for with the QR project!
3427
Leif Sieben @leif7ieben.bsky.social · 05/06/2025
change my mind: bruot RIS to Bibtex converter is the best website ever built. www.bruot.org/ris2bib/
bruot.org
Online RIS to BibTeX converter
The simple RIS (EndNote) to bib (BibTeX) online conversion app.
001
Leif Sieben @leif7ieben.bsky.social · 28/05/2025
You know volatility is going crazy when sitting down to write a PAC proof about the sampling efficiency of an active-learning algorithm feels like a therapy session. At least math hasn't changed over the past 12 months ...
021
Reposted by Leif Sieben
Andrew S. Rosen @andrewrosen.bsky.social · 23/05/2025
Not me accidentally typing `squeue` into the Facebook chat.
081
Reposted by Leif Sieben
Martin Stoermer @martinstoermer.bsky.social · 16/04/2025
Thought experiments that you have down the pub are in vino
011
Leif Sieben @leif7ieben.bsky.social · 16/04/2025
Has anybody ever paused to think that the glass that is metonymically meant by “in vitro” is actually also just made of silicon and could just as well be called “in silico”?
230
Reposted by Leif Sieben
Christian Odendahl @codendahl.bsky.social · 10/04/2025
Do I really write "... reckons Deutsche Bank, a German bank"?
28933
Reposted by Leif Sieben
Encephalophatass (Any pronouns) @encephalophatass.bsky.social · 03/04/2025
It’s always “We launched these tardigrades into space!” “We froze them to absolute zero!” “We threw them into an erupting volcano!” Never “We took these tardigrades on a holiday. They’re getting tiny massages and sipping little umbrella drinks on the beach.”
241885495
Leif Sieben @leif7ieben.bsky.social · 26/03/2025
One day ChatGPT is going to learn to use MorganGenerator ... not today though.
200
Reposted by Leif Sieben
Christian Odendahl @codendahl.bsky.social · 25/03/2025
Very true.
2131
Reposted by Leif Sieben
Martin Pacesa @martinpacesa.bsky.social · 23/03/2025
If a protein unfolds and there is no one to measure the CD spectrum, did it really unfold?
2292
Leif Sieben @leif7ieben.bsky.social · 20/03/2025
It's such a privilege to live in a time where I can fully pretend like the climate crisis isn't happening simply by living in constant existential fear about the replacement of all meaningful work by more powerful, intelligent systems. Oh and somebody said something about a recession?
020
Leif Sieben @leif7ieben.bsky.social · 18/03/2025
I know Manus AI didn't hit the mark but with everybody rushing into agentic AI, I'm genuinely at the point where I'm wondering whether I need to get PhD applications out pre-singularity. Who still hires PhDs if they can have a 24/7 researcher which inputs a PI's command and outputs results/data?
120
Reposted by Leif Sieben
Pedro Beltrao @pedrobeltrao.bsky.social · 16/03/2025
New blog post - State of the lab 12, yearly series on being a group leader in academia. This one reflects back on the transition from junior PI to a more established scientist www.evocellnet.com/2025/03/stat...
evocellnet.com
State of the lab 12 - Becoming an established scientist
This blog post is part of a (nearly) yearly series on running a research group in academia. This post summarizes year 12, the 3rd year afte...
23911
Reposted by Leif Sieben
Alex Selby-Boothroyd @alexselbyb.bsky.social · 15/03/2025
The New Yorker is reäppraising the internet age
2203
Reposted by Leif Sieben
Rachael Sirianni, PhD @docsirianni.bsky.social · 15/03/2025
This is horrible to post, but I may as well post it. We are essentially shutting down research operations in my group, which is focused on treatments for pediatric brain cancer. I’m a well funded investigator, and there’s no choice. Science can’t function without the stability of NIH
7072654610664
Leif Sieben @leif7ieben.bsky.social · 15/03/2025
In 20-30 years time, I wonder whether my children will look back on 2024 or 2025 the same way that I look back on 1968.
110
Reposted by Leif Sieben
The Onion @theonion.com · 18/02/2025
87% Of Loud Crashing Noises Are Nothing, Report Top Experts From Other Room theonion.com/87-of-l...
87% Of Loud Crashing Noises Are Nothing, Report Top Experts From Other Room
273581391
Reposted by Leif Sieben
lukelukeluke @lukelukeluke.bsky.social · 09/02/2025
You have never felt relief like a homeless hermit crab the moment they’re safe inside a new shell
75239096
Reposted by Leif Sieben
Katie Wilkinson @drkwilkinson.bsky.social · 09/02/2025
Helpful table to determine how much your University or health system is set to lose if the NIH indirect cap is suddenly lowered to 15%. For SJSU it is $374k which is on the smaller end but devastating considering our other budget issues. datawrapper.dwcdn.net/l0ZqA/8/
datawrapper.dwcdn.net
Estimated Single Year Loss of NIH Funding if 15% Indirect Cost Rate is Imposed
Based on analysis of 2024 NIH funding data. Sums are totals of losses in funding to programs if indirect costs had been capped at 15%
14214129
Reposted by Leif Sieben
Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 01/02/2025
Ask an LLM to summarize your paper because some reviewer will for sure read your paper this way
3525
Leif Sieben @leif7ieben.bsky.social · 01/02/2025
The title of the month award goes to...
120
Reposted by Leif Sieben
Kosta Derpanis @csprofkgd.bsky.social · 01/02/2025
The hottest new programming language is E̶n̶g̶l̶i̶s̶h̶ Mandarin #DeepSeek
092
Leif Sieben @leif7ieben.bsky.social · 29/01/2025
Has anybody’s ChatGPT also been starting to use an uncommon amount of emojis? Is this meant to lure me back from Deepseek?
000
Reposted by Leif Sieben
Randall Munroe @xkcd.com · 21/01/2025
Chemical Formulas xkcd.com/3040
346255652044
Reposted by Leif Sieben
Shaun O’Boyle @shaunoboyle.bsky.social · 16/01/2025
Why do I have to rent software? Why can't I just buy it?
0292