Benjamin Manning (@BenSManning) / X

Benjamin Manning

1,000 posts

Benjamin Manning

@BenSManning

Phd Student @MIT | Economics, AI, & Behavioral Science | Research: benjaminmanning.com

Cambridge, MA

Joined February 2022

Pinned
Benjamin Manning
@BenSManning
Sep 3, 2025
Brand new paper with @johnjhorton that I'm very excited to share: "General Social Agents" Suppose we wanted to create AI agents for simulations to make predictions in never-before-seen settings. How might we do this? We explore an approach to answering that question!
140K
Benjamin Manning
@BenSManning
Aug 19, 2024
Never has a book, nor even an entire course, improved my intuition about all things ML. Every page left me a better understanding of topics I've spent years studying. Maybe this reflects bad courses or my low IQ, but I think the book is just that good. Must read.
83K
Benjamin Manning
@BenSManning
Aug 29, 2025
We have a brand new paper we're hoping to make public next week! Here is the title and abstract. If you'd like to get an early copy (& provide feedback 🙏) see next tweet for signup link ... 1/
39K
Benjamin Manning
@BenSManning
Apr 21, 2024
fwiw, really appreciated the dialogue here, we are excited to discuss---both the positives and the critiques. There is so much unknown with these models and their potential to improve our methods for social inquiry, but we won't know whats good---or bad--- until we explore.
Ethan Mollick
@emollick
Apr 21, 2024
Yeah, gonna delete this. People are just insulting the paper authors without reading the paper or understanding the context of the fields being discussed. They didn’t ask that I tweet about them, and I didn’t expect the tweet to travel so widely. Getting nasty on Twitter.
30K
Benjamin Manning
@BenSManning
Jul 22, 2024
Proud of our new paper on prompting & GenAI advances! My Big takeaway: AI keeps making us humans better in unexpected, exciting ways. Presumably, this will open up further opportunities for us to leverage and benefit from this technology! bit.ly/3YdExbt
9K
Benjamin Manning
@BenSManning
Oct 25, 2024
I put the Gode and Sunder (1993) zero intelligence trader paper into the new Claude and asked it to make me a simulation replicating the paper. One short prompt - full web app that (more or less) works:
Enhanced Double Auction Market Simulator
From claude.ai
19K
Benjamin Manning
@BenSManning
May 3, 2024
First paper on NBER---hopefully many more to come! So thankful for brilliant collaborators like @johnjhorton and @Kehang_Zhu, I don't know how they function in society being so smart ;)
NBER
@nberpubs
May 3, 2024
Using large language models both as an experimental subject but also as a scientist, from @BenSManning, @Kehang_Zhu, and @johnjhorton nber.org/papers/w32381
7.5K
Benjamin Manning
@BenSManning
Apr 2, 2024
let the record show that I am this grad student, and @johnjhorton has also asked me if I've seen memento at least 5x (maybe more, now I can't remember...) Great movie btw
John Horton
@johnjhorton
Apr 2, 2024
I told a grad-student co-author "try to imagine me as the guy from 'Memento' who can't remember anything & needs clues to pick-up the thread on projects" and they said "I believe you, because you already used that memento analogy"
11K
Benjamin Manning
@BenSManning
Sep 3, 2025
Replying to @BenSManning
Optimized agents predict the human responses far better than an off-the-shelf baseline LLM (3x) and relevant game-theoretic equilibria (2x). In 86% of the games, all human subjects chose a strategy in support of the LLM simulations; only 18% were in support of the equilibria.
44K
Benjamin Manning
@BenSManning
Sep 12, 2024
I always thought this one was one of the least intuitive econ problems around. o1-preview NAILS it. 1/3
18K
Benjamin Manning
@BenSManning
Nov 6, 2025
Agreed - refine is amazing. Their margins must be absurd (75% +?). I’ve heard that startups only appealing to academics don’t make $, but this has gotta be $$$… for @ben_golub and co… so epic. Is this a pattern (niche market, huge margin?) that will continue? Or am I wrong
27K
Benjamin Manning
@BenSManning
Apr 19, 2024
Automated Social Science: Language Models as Scientist and Subjects now on arxiv! With @Kehang_Zhu @johnjhorton
arxiv.org
Automated Social Science: Language Models as Scientist and Subjects
We present an approach for automatically generating and testing, in silico, social scientific hypotheses. This automation is made possible by recent advances in large language models (LLM), but...
4.3K
Benjamin Manning
@BenSManning
Mar 2, 2024
Feedback welcome! Still working on the draft for submission :)
John Horton
@johnjhorton
Mar 2, 2024
New working paper by @BenSManning & @Kehang_Zhu that & I’m super excited about benjaminmanning.io/files/rs.pdf
9.6K
Benjamin Manning
@BenSManning
Jul 17, 2024
Tune in to @johnjhorton presenting our automated social science paper (with @Kehang_Zhu) @nberpubs summer institute at 2:10 EST today. Really excited to be here for this - I'm hoping there will be a lively debate! Live stream will be at this link: youtube.com/nbervideos
2.5K