1 code implementation • 24 Jan 2024 • T. Ben Thompson, Zygimantas Straznickas, Michael Sklar
EPO optimizes the input prompt to simultaneously maximize the Pareto frontier between a chosen internal feature and prompt fluency, enabling fluent dreaming for language models.
no code implementations • 7 Jul 2023 • Stephen Bates, Michael I. Jordan, Michael Sklar, Jake A. Soloff
We show how the principal can conduct statistical inference that leverages the information that is revealed by an agent's strategic behavior -- their choice to run a trial or not.
no code implementations • 13 May 2022 • Stephen Bates, Michael I. Jordan, Michael Sklar, Jake A. Soloff
The efficacy of the drug is not known to the regulator, so the pharmaceutical company must run a costly trial to prove efficacy to the regulator.