LESSWRONGTags
LW

Aligned AI Proposals

•

Applied to How to safely use an optimizer by Mateusz Bagiński 1mo ago

•

Applied to Strong-Misalignment: Does Yudkowsky (or Christiano, or TurnTrout, or Wolfram, or…etc.) Have an Elevator Speech I’m Missing? by Benjamin Bourlier 2mo ago

•

Applied to Alignment in Thought Chains by Faust Nemesis 2mo ago

•

Applied to Update on Developing an Ethics Calculator to Align an AGI to by sweenesm 2mo ago

•

Applied to Requirements for a Basin of Attraction to Alignment by RogerDearnaley 3mo ago

•

Applied to Alignment has a Basin of Attraction: Beyond the Orthogonality Thesis by RogerDearnaley 3mo ago

•

Applied to Proposal for an AI Safety Prize by sweenesm 3mo ago

•

Applied to Goodbye, Shoggoth: The Stage, its Animatronics, & the Puppeteer – a New Metaphor by RogerDearnaley 4mo ago

•

Applied to Moral realism and AI alignment by Caspar Oesterheld 4mo ago

•

Applied to Striking Implications for Learning Theory, Interpretability — and Safety? by RogerDearnaley 4mo ago

•

Applied to Safety First: safety before full alignment. The deontic sufficiency hypothesis. by RogerDearnaley 4mo ago

•

Applied to Motivating Alignment of LLM-Powered Agents: Easy for AGI, Hard for ASI? by RogerDearnaley 4mo ago

•

Applied to AI Alignment Metastrategy by Gunnar_Zarncke 4mo ago

•

Applied to Gaia Network: a practical, incremental pathway to Open Agency Architecture by Roman Leventov 4mo ago

•

Applied to Interpreting the Learning of Deceit by RogerDearnaley 4mo ago

•

Applied to Scalable Oversight and Weak-to-Strong Generalization: Compatible approaches to the same problem by RogerDearnaley 4mo ago

•

Applied to Language Model Memorization, Copyright Law, and Conditional Pretraining Alignment by RogerDearnaley 5mo ago