flâneur

Recommendations-for-Using-Red-Teaming-for-AI-Accountability-PolicyBrief.pdf

datasociety.net · 3,341 words · saved by 1 readers

N/A

POLICY BRIEF AI Red-Teaming Is Not a One-Stop Solution to AI Harms: Recommendations for Using Red-Teaming for AI Accountability Sorelle Friedler, Ranjit Singh, Borhane Blili-Hamelin, Jacob Metcalf, and Brian J. Chen AI Red-Teaming is Not a One-Stop Solution to AI Harms: Recommendations for Using Red-Teaming for AI Accountability Red-teaming is a method where people — traditionally security engineers inside a company — interact with a system to try to make it produce undesired outcomes. The goal is to identify ways the system doesn’t work as intended, and then find fixes for the…

related reading