LESSWRONGTags
LW

Conservatism (AI)

•
Applied to "Corrigibility at some small length" by dath ilan by Christopher King 2mo ago
•
Applied to [Intro to brain-like-AGI safety] 14. Controlled AGI by Steven Byrnes 1y ago
•
Applied to Conservative Agency with Multiple Stakeholders by Multicore 2y ago
•
Applied to Solving the whole AGI control problem, version 0.0001 by Steven Byrnes 2y ago
•
Applied to Formal Solution to the Inner Alignment Problem by michaelcohen 2y ago
•
Applied to Conservatism in neocortex-like AGIs by Steven Byrnes 3y ago
•
Applied to "Learning to Summarize with Human Feedback" - OpenAI by Multicore 3y ago
•
Applied to Pessimism About Unknown Unknowns Inspires Conservatism by Multicore 3y ago
•
Applied to RFC: Philosophical Conservatism in AI Alignment Research by Multicore 3y ago
•
Created by Multicore at 3y