AI-Powered Simulation and Human Behavioral Research Are Almost Certainly Complements
Either/or is not the right way to think about using AI simulations
Disarming the Slop Cannon (ironically, with AI)
Using Expected Parrot to spin up bespoke AI interview + analysis workflows to flag “authors” who can’t explain their own work
A Fake Pharmacy Scenario: From AI to Humans and Back Again (in under 2 hours, using 71¢ worth of tokens)
Using Expected Parrot to riff on a recent WSJ article on how CVS is using digital twins
AI Thinks this Post is Terrible (but I’m writing it anyway)
Using Expected Parrot to propose and prioritize blogging topics
[Nerd Stuff]: Research Surveys should be Version-controlled files
And with Expected Parrot, they are!
We can do that! Best Practices for Dealing with Randomness in Language Model Outputs
How Expected Parrot embodies many best practices out of the box
Twitter Proposes; Prolific Disposes - Part I
Using Expected Parrot to test "promising" Ideas with real humans
Marginal Ideas
Using Expected Parrot to find clusters of opportunities
Your Ideas Are Terrible---Find Out Cheaply, in Private
Your Ideas Are Terrible---Find Out Cheaply, in Private
Using Expected Parrot for "pre-mortem" simulations
A Patriotic Experiment in AI-Powered Research
Expected Parrot can be used for reproducible data labeling.
Test Your Survey on Synthetic Respondents Before You Waste a Single Real One
How to do this easily with Expected Parrot