🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Introducing Project Sid: the first simulations of 1000+ truly autonomous agents collaborating in a virtual world, w/ emergent economy, culture, religion, and government Humans are the only species to land the moon, because we can cooperate at a vast scale Can AI do the same?

very fun (and very timely!!) new paper led by Nicolò De Sabbata — we use principles from cogsci to improve reasoning efficiency in LLMs. Get that CoT gain without breaking the bank! 💸💸💸

Social media challenge day2!! Princeton HCI Group photo with UIST vet professors! ACM UIST #UISTChallenge #UIST2024 Prof. Adam Finkelstein Prof. Parastoo Abtahi Mohamed Kari Lei Zhang Ching-Yi Tsai daisy daekun kim Cyrus Vachha Ryan Liu Yuhan Liu @XingjianZhang6 Ruyu Yan

I am recruiting 1-2 PhD students for Fall 2025 at Princeton to work on Comp Social Science/Societal Impact of GenAI/GenAI for SocSci I wrote a bit about my research flavor & interests here: manoelhortaribeiro.github.io/advising Deadline: December 15th (cs.princeton.edu/grad#prospecti…) Please boost!

Academic job market post! 👀 I’m a CS Postdoc at Stanford in the Stanford Human-Computer Interaction Group group. I develop ways to improve the online information ecosystem, by designing better social media feeds & improving Wikipedia. I work on AI, Social Computing, and HCI. piccardi.me 🧵

Simulating human behavior with AI agents promises a testbed for policy and the social sciences. We interviewed 1,000 people for two hours each to create generative agents of them. These agents replicate their source individuals’ attitudes and behaviors. 🧵arxiv.org/abs/2411.10109

So thrilled to share our work on this~! Grounding generative agents in real, verifiable behavior is the step that takes this method from producing simulacra to creating simulations that capture the richness of human experiences.

Do reviewers appropriately update their scores based on rebuttals? In this PLOS ONE paper with Ryan Liu, Steven Jecmen, Fei Fang, and Nihar Shah, we present a randomized controlled trial that suggests that, at least under certain conditions, they do. journals.plos.org/plosone/articl…

Simulating future outcomes of people's interactions with AI reduces deception... Because eventually the person will find out! 🙃 Great application of simulation, really enjoyed working on the project with @kevin_lkq Haimin Hu Griffiths Computational Cognitive Science Lab & Jaime

Constitutional AI works great for aligning LLMs, but the principles can be too generic to apply. Can we guide responses with context-situated principles instead? Introducing SPRI, a system that produces principles tailored to each query, with minimal to no human effort. [1/5]

OpenAI has launched Operator, an agent that can perform tasks in your browser. I asked it to complete a Qualtrics survey I created. The results are very promising for Operator but *very* concerning for survey researchers

Todo lists, docs, email style – if you've got individual or team knowledge you want ChatGPT/Claude to have access to, Knoll (knollapp.com) is a personal RAG store from Stanford University that you can add any knowledge into. Instead of copy-pasting into your prompt every time,

Should we use LLMs 🤖 to simulate human research subjects 🧑? In our new preprint, we argue sims can augment human studies to scale up social science as AI technology accelerates. We identify five tractable challenges and argue this is a promising and underused research method 🧵

Using LLMs to build AI scientists is all the rage now (e.g., Google’s AI co-scientist [1] and Sakana’s Fully Automated Scientist [2]), but how much do we understand about their core scientific abilities? We know how LLMs can be vastly useful (solving complex math problems) yet