AI ALIGNMENT FORUM
Tags
AF

Instrumental Convergence

•

Applied to Why Recursive Self-Improvement Might Not Be the Existential Risk We Fear by Nassim_A 1mo ago

•

Applied to Stone Age Herbalist's notes on ant warfare and slavery by trevor 2mo ago

•

Applied to Galatea and the windup toy by Nicolas Villarreal 2mo ago

•

Applied to The murderous shortcut: a toy model of instrumental convergence by Thomas Kwa 3mo ago

•

Applied to A framework for thinking about AI power-seeking by RobertM 5mo ago

•

Applied to Ted Kaczyinski proves instrumental convergence? by xXAlphaSigmaXx 6mo ago

•

Applied to "If we go extinct due to misaligned AI, at least nature will continue, right? ... right?" by plex 8mo ago

•

Applied to Building selfless agents to avoid instrumental self-preservation. by blallo 1y ago

•

Applied to Alignment, conflict, powerseeking by Oliver Sourbut 1y ago

•

Applied to Natural Abstraction: Convergent Preferences Over Information Structures by paulom 1y ago

•

Applied to What are some examples of AIs instantiating the 'nearest unblocked strategy problem'? by Ruben Bloom 1y ago

•

Applied to Instrumental Convergence and human extinction. by Spiritus Dei 1y ago

•

Applied to Destroying the fabric of the universe as an instrumental goal. by AI-doom 1y ago

•

Applied to Instrumental Convergence Bounty by Logan Zoellner 1y ago