Hi #EconTwitter! 📈 Keen on the latest in causal inference with panel data models? Check out 👇 this new #econometrics survey by Dmitry Arkhangelsky (CEMFI) and guido imbens (@stanford)! It covers everything from difference-in-differences and two-way-fixed-effect

I've been using ChatGPT to help me filter new arXiv papers every day for two months. It saved me a lot of time and allowed me to stay on top of the field's development. In case you want to try: github.com/yang3kc/daily_… Here is how it works: 1/5

I think there's maybe really something here, look at this. I got GPT to respond to the prompt from this uml.edu/docs/sample-es…. Then I got a sequence of embeddings for each word in both the human- and GPT- authored essays. You can see how the human one moves around more.

What can LLMs bring to the study of cultural evolution? 🤔 In this preprint, we present a framework for simulating cultural evolution using LLMs 🦜 We study how the dynamics depends on social structure, simulated personalities👥, and whether it has potential attractors🧲🔍 1/17

Any accounts doing engagement farming will be suspended and traced to source

No ....

GPT-4o would not have happened without the vision, talent, conviction, and determination of Prafulla Dhariwal over a long period of time. that (along with the work of many others) led to what i hope will turn out to be a revolution in how we use computers.

All ChatGPT Free users can now use browse, vision, data analysis, file uploads, and GPTs.

Introducing OpenAI for Nonprofits, a new initiative to make our tools more accessible to nonprofit organizations. openai.com/index/introduc…

We’re partnering with Apple to integrate ChatGPT into iOS, iPadOS, and macOS—coming later this year: openai.com/apple

What's the current status of causal inference in political science? Since the advent of the credibility revolution social scientists pay more attention to establishing cause-and-effect relationships. But how has poli sci responded to the new methods and trends? (1/n)

Is OpenAI lying about the GPT-4o-mini cost? I used GPT-4o and GPT-4o-mini with the same exact system prompt and the same exact image input GPT-4o input tokens: 500 GPT-4o-mini input tokens: 14,242 FOR THE SAME EXACT IMAGE That's a 28x increase in input tokens 🤯 I checked

Troy 🎮 OpenAI The dollar price per image is the same for GPT-4o and GPT-4o mini. To maintain this, GPT-4o mini uses more tokens per image. Thank you for your observation!

i'm losing my s*** OpenRouter Has a totally free 130,000 context model. FREE. this flips my mind.

I'll be giving a short talk on "Evaluating Generative AI Systems is a Social Science Measurement Challenge" (arxiv.org/abs/2411.10939) at 230pm today at the Microsoft Research booth! #NeurIPS2024

Want to add an LLM chatbot to your Qualtrics surveys? Here's a step-by-step guide showing exactly how to do this with AWS Bedrock joshuakalla.github.io/llm_persuasion/

Our computer vision textbook is now available for free online here: visionbook.mit.edu We are working on adding some interactive components like search and (beta) integration with LLMs. Hope this is useful and feel free to submit Github issues to help us improve the text!

When Can We Use Two-Way Fixed-Effects (TWFE): A Comparison of TWFE and Novel Dynamic Difference-in-Differences Estimators. arxiv.org/abs/2402.09928