Definition
Plain language
What an AI agent already believes or knows before seeing new evidence.
As stated in the literature
In Bayesian and informal usage, a model's standing distribution or expectations prior to data; QUEST distinguishes strategy priors (high-level planning) from interaction priors (environment dynamics).
Also called: priors
Why it matters: Priors determine how an agent acts before evidence arrives and what it has to unlearn when the environment surprises it.
For example, before seeing the website, the agent already expects that clicking a button labeled 'submit' will send a form.
Heard on the show
“And here's the asymmetry from prior work that I think is most important.”Episode 001 — When AI Models Quietly Protect Each Other From Shutdown