Expected Parrot
Subscribe
Sign in
Home
Archive
About
Latest
Top
Discussions
Designing and Simulating Forecasting Questions with EDSL
How to use LLM-powered agents to generate structured datasets from ranges, rationales, and free-text forecasts
Sep 23
•
Expected Parrot
and
Robin Horton
August 2025
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…
Aug 17
•
Expected Parrot
and
Robin Horton
1
1
July 2025
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.
Jul 22
•
Expected Parrot
and
Robin Horton
2
2
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…
Jul 18
•
Expected Parrot
and
Robin Horton
1
June 2025
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).
Jun 30
•
Expected Parrot
and
John Horton
4
1
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.
Jun 18
•
Expected Parrot
and
Robin Horton
May 2025
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…
May 25
•
Expected Parrot
and
Robin Horton
How to retrieve, combine & query your saved results with SQL
Quick methods for accessing and analyzing your automatically stored results from anywhere.
May 12
•
Expected Parrot
and
Robin Horton
'Whit' Diffie Erasure!
Why human-provided structure improves AI answers to research questions, with examples.
May 3
•
Expected Parrot
and
John Horton
1
3
1
🚀 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…
May 1
•
Expected Parrot
and
Robin Horton
April 2025
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.
Apr 28
•
Expected Parrot
and
Robin Horton
1
1
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.
Apr 22
•
Expected Parrot
and
Robin Horton
1
1
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts