Newsletter
Designing and Simulating Forecasting Questions with EDSL
How to use LLM-powered agents to generate structured datasets from ranges, rationales, and free-text forecasts
John Horton
Newsletter
Teaching AI simulations? Get free credits for your students and research projects.
We have ready-to-use materials for teaching LLM-based simulations with our open-source tools, and free credits for getting started. Earn more free credits by sharing your referral code!
Newsletter
How to launch a survey with LLMs and humans
Our tools let you design and run the same survey with AI agents and human respondents, and seamlessly compare results.
Newsletter
Bring your own keys or mix and match
A key feature of Expected Parrot is that you can always use your own keys for LLMs and human participant platforms, or you can use your Expected Parrot key for unified access.
Newsletter
Why AI social simulations will be transformative
The Simulmatics corporation, founded in 1959, aimed to predict the future using simulations (it's right there in the company name). Those simulations could be run on newly available digital computers, informed by the micro-data that was, by then, routinely collected and digitized. Applications were wide and spanned
Newsletter
Do I have time for this?
Our tools look technical and emphasize tinkering over quick answers. Here's why I still think you should try them.
Newsletter
Validate your LLM answers with real respondents
Here's a quick example of methods for generating a web-based version of your LLM survey and analyzing human and LLM responses together at your workspace.
Newsletter
How to retrieve, combine & query your saved results with SQL
Quick methods for accessing and analyzing your automatically stored results from anywhere.
Newsletter
'Whit' Diffie Erasure!
Why human-provided structure improves AI answers to research questions, with examples.
Newsletter
🚀 Over 1 million Q&A cached and counting
The Universal Remote Cache now has over a million unique LLM prompts and responses. You can retrieve them at no cost whenever you replicate research at Expected Parrot.
Newsletter
New features for monitoring your AI research costs
Our tools are designed to make it easy to understand and monitor your LLM usage. Learn more about our latest features for precisely tracking your costs.
Newsletter
I want to see how OpenAI's o3 compares to...
EDSL is an open-source tool that lets you readily compare performance for many language models at once.