Subscribe
Sign in
Home
Podcast
Chat
Difference-in-Differences
Mixtape University
The Mixtape Mailbag
Mixtape Sessions
Pedro's Diff-in-Diff Checklist
History of Economics
Claude Code
About
Latest
Top
Discussions
Claude Code 20: Faculty Adoption of AI, Decks and Folders, and Non-Trivial Security Risks
I recently gave a talk to a small group at Baylor about getting faculty to adopt AI.
Feb 17
•
scott cunningham
22
16
3
Codechella Madrid Week 2: New Material and Claude Code
This is the second in my weekly Monday series on Codechella Madrid (May 25-28, 2026).
Feb 16
•
scott cunningham
3
3
1
Closing out more tabs: the day after valentines edition
I hope everyone had a happy valentines weekend and that you were not party into massacres, only lovely evenings with laughter and tenderness, from…
Feb 15
•
scott cunningham
7
1
1
Closing out my tabs: Valentines Day edition
Welcome to that time of the week when I take far too many tabs I’ve left open, post them here, and then make the strenuous effort to close them from my…
Feb 14
•
scott cunningham
9
1
Claude Code 19: When the Reclassification Is Massive But the Trends Don't Change, Something Interesting Is Happening (Part 4)
Testing the marginal-cases hypothesis with a thermometer, and letting Claude Code run wild on datasets
Feb 13
•
scott cunningham
6
1
1
Claude Code 18: When the Reclassification Is Massive But the Trends Don’t Change, Something Interesting Is Happening
Digging into why a $11 LLM replication of a PNAS paper works at all
Feb 12
•
scott cunningham
12
3
1
Claude Code 17: The Zero Profit Condition Is Coming
Substack reasoning about who the new equilibrium
Feb 10
•
scott cunningham
29
16
2
Codechella Madrid is Back — May 25-28 at CUNEF
I’m late.
Feb 9
•
scott cunningham
5
Claude Code 16: The Memory Foam Mattress Theory of Claude Code
Plus a beautiful deck describing my workflow
Feb 8
•
scott cunningham
13
10
5
Closing tabs: the Saturday edition
A lot of links to articles about excessive flatulence, time series and causal inference, Claude code, noncompetes, valentine’s day presents, tons of…
Feb 7
•
scott cunningham
6
3
2
Claude Code 15: The Results Are In: Can LLMs Replicate a PNAS Paper? (Part 2)
69% agreement, $11, and 2.6 hours later
Feb 6
•
scott cunningham
16
15
6
Claude Code Part 14: I Asked Claude to Replicate a PNAS Paper Using OpenAI's Batch API. Here's What Happened (Part 1)
A case study in pushing Claude Code to do something genuinely hard
Feb 5
•
scott cunningham
21
6
2
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
