Too Lazy to Read the Paper

In this video I talk to YY Ahn about using Claude Code for Research. 

Normally in Too Lazy to Read the Paper, somebody explains a paper to me, because reading papers is hard and talking to people is fun and natural.
   
And if someone's too lazy to read the paper, they're definitely too lazy to read the manual. 

So today there's a new format. There's no paper. Instead there's a thing we're all talking about in the shadows – agentic coding, Claude Code. The whole business of handing an AI your research and letting it write and run the code – and my sense is that getting started on this is a big hurdle to a lot of folks. So to help them (and myself, I'm sitting down with all-round genious, renessaince man, deep thinker, conneseur of all things coding and living in the terminal, and honest, decent person, YY Ahn.
   
YY is
* Quantitative Foundation Distinguished Professor
* School of Data Science
* University of Virginia

We cover the following topics
* Intro to YY
* Brief intro to Claude Code … what even is it?
* Working in the terminal
* Claude as reviewer zero
* Submitting to arXiv, checking references
* Some science use-cases 
* The concrete setup … remote control, etc. What about context windows, should Claude be re-started once in a while? Do you have tasks that run on a schedule.
* What about Gemini or ChatGPT as an alternative. Having interchangble coding engines.
* Should one have a local model that the AI can direct.
* Cool tips & tricks for making life easier
* Discussion about what this does to science, where can humans still make a difference
*Discussion about de-skilling

I am super excited to have David Lazer (1,2) on the pod today. 

David Lazer needs no introduction. But here at lazypod we’re polite, so he get’s one anyway.

David Lazer is a University Distinguished Professor of Political Science and Computer Sciences, Northeastern University, and Co-Director, NULab for Texts, Maps, and Networks. Prior to coming to Northeastern University, he was on the faculty at the Harvard Kennedy School (1998-2009). In 2019, he was elected a fellow to the National Academy of Public Administration.

His research has been published in such journals as Science, Nature, Proceedings of the National Academy of Science, the American Political Science Review, Organization Science, and the Administrative Science Quarterly, and has received extensive coverage in the media, including the New York Times, NPR, the Washington Post, the Wall Street Journal, and CBS Evening News.

He is among the leading scholars in the world on misinformation and computational social science and has served in multiple leadership and editorial positions, including as a board member for the International Network of Social Network Analysts (INSNA), reviewing editor for Science, associate editor of Social Networks and Network Science, numerous other editorial boards and program committees.

As always we talk about David path through science, with a particular emphasis on Computational Social Science (3) - a field that he has been absolutely instrumental in establishing. But we also cover many other topics in this wide-ranging converstation which ends up covering his paper “Product diffusion through on-demand information-seeking behaviour” (4) which is one of his favorite papers and least cited, and which has a super-interesting backstory.

References
(1) https://lazerlab.net
(2) https://cssh.northeastern.edu/faculty/david-lazer/
(3) https://www.science.org/doi/10.1126/science.1167742
(4) https://royalsocietypublishing.org/doi/full/10.1098/rsif.2017.0751

Holy cow, it was great to chat with Brennan Klein (1). It’s another renaissance person on the Pod.

In his research, Brennan attempts to understand how complex systems are able to represent, predict, and intervene on their surroundings across a number of different scales—all in ways that appear to maintain the statistical boundary between them and their environment.

He uses this approach to study a range of phenomena from decision making, to experimental design, to causation and emergence in networks.

Brennan is currently working with Professors Alessandro Vespignani and Sam Scarpino on a research examining the teleology of networks, or why there appears to be an apparent purpose or goal-directedness to the dynamics and structure of networks.

He received a BA in Cognitive Science and Psychology from Swarthmore College in 2014, studying the relationship between perception, action, and cognition.  I received my PhD in Network Science from Northeastern University in 2020.

Now he’s  a postdoc at the Network Science Institute, Northeastern University, he’s a senior researcher at Verses Inc (2) and he’s a Data for Justice Fellow at Institute for the Study of Policing, Incarceration, and Public Safety; The Hutchins Center for African & African American Research at a small university, Harvard.

With those two postdoc advisors, it should come as no surprise that during COVID, Brennan has a number of important COVID related publications as well.

We talk about his paper “Network comparison and the within-ensemble graph distance” (3) but there’s so much more!!

And finally Brennan makes art under the pseudonym JK Rofling (4). I urge every single one of you to go check out his art. It’s great. And I totally didn’t get to ask him about it. Because we spent so much time covering the many other exciting things Brennan has got going on.

References
(1) https://www.jkbrennan.com
(2) https://www.verses.io
(3) https://royalsocietypublishing.org/doi/10.1098/rspa.2019.0744
(4) https://www.jkrofling.com

Today we’re in for something a little bit different. Our guest is “Erik Hoel”, who’s not only a scientist, but also an exciting writer of books and essays. I read his fantastic first book “The Revelations” (1,2) last winters … and when I visited Boston this summer, I took a chance and sought him out. He graciously agreed to chat.

For this interview I traveled out to Erik’s house that’s placed down along a long gravel road and surrounded by lakes and trees on Cape Cod. And we chatted in his first floor study surrounded by a classy collection of books.

So who is Erik? This audience may know him as a research assistant professor at Tufts University in Boston. But that’s only a small part of his story. Erik grew up in his family's independent bookstore, Jabberwocky Bookshop, and this experience has stayed with him, motivating him to write books, reviews, and essays.

At college he became interested in solving the scientific problem of consciousness and ended up receiving his PhD in neuroscience at the University of Wisconsin-Madison. We spend a good chunk of time in the podcast with me learning about consciousness from Erik.

Later he was a postdoctoral researcher at Columbia University and a visiting scholar at the Institute for Advanced Study in Princeton. Alongside his academic accolades, Erik was named one of Forbes 30 Under 30 and in 2017 he was chosen as a NYC Emerging Writers Fellow for his short stories.

My interview with Erik is different from what I normally do on the Pod. We do cover his past and motivations, but I actually did read his book, and we talk about that. As well as the writing process - and the creative process - in some detail.

I also want to flag up that Erik is a great thinker and essayist. You can find his stuff on his substack “The Intrinsic Perspective” (3). I love all of his writing, but a particular favorite is his recent award-winning book review (4), which among other thing proposes a new theory for why human civilization took a while to get off the ground … and why Twitter might be taking us back to the roots. I highly recommend that you check out his writing.

References
(1) https://www.erikphoel.com
(2) https://www.amazon.com/Revelations-Novel-Erik-Hoel/dp/1419750224
(3) https://erikhoel.substack.com
(4) https://erikhoel.substack.com/p/the-gossip-trap

PS In the beginning of the podcast, we talk about how I first became aware of Erik. In case you’re interested, the whole thing is described here https://sunelehmann.com/2022/01/09/oh-twitter/

Today on the Pod we are lucky to have Laura Alessandretti (1) visiting us.

Laura is an Assistant Professor in Modelling of Human Dynamics at the Technical University of Denmark. She is interested in Computational Social Science, Data Science and Complex Networks. She studies aspects of human behavior combining analysis of large-scale datasets, analytical models and numerical simulations.

Previously, she was a PostDoctoral researcher at the Copenhagen Centre for Social Data Science and at DTU Compute. Before that, Laura got her PhD in Mathematics at City, University of London, and her Master's in Physics of Complex Systems at École normale supérieure de Lyon. She’s also doing many things to serve the scientific community, for example Laura will be the general chair (with Luca Aiello) of the IC2S2 conference in Copenhagen.

Laura is a close collaborator and a good friend of mine, so today’s podcast is a little bit different than many others. We discuss the long and winding road leading to our joint paper “The Scales of Human Mobility” (2).

The sound is a little less perfect than sometimes, but the content is top-notch, so I hope you’ll stick with it in spite of that.

References
(1) https://laura.alessandretti.com
(2) https://www.nature.com/articles/s41586-020-2909-1