Outer Alignment

Applied to The Metaethics and Normative Ethics of AGI Value Alignment: Many Questions, Some Implications by Dario Citrini at 5d

Applied to Alignment via manually implementing the utility function by Chantiel at 12d

Applied to Distinguishing AI takeover scenarios by Samuel Dylan Martin at 13d

Applied to Call for research on evaluating alignment (funding + advice available) by Beth Barnes at 21d

Applied to Is it worth making a database for moral predictions? by Spiralling at 1mo

Applied to Thoughts on a "Sequences Inspired" PhD Topic by goose000 at 3mo

Applied to MIRIx Part I: Insufficient Values by Arun Jose at 3mo

Applied to Game-theoretic Alignment in terms of Attainable Utility by Jacob Stavrianos at 4mo

Applied to Thoughts on the Alignment Implications of Scaling Language Models by larai at 4mo

Applied to Controlling Intelligent Agents The Only Way We Know How: Ideal Bureaucratic Structure (IBS) by Justin Bullock at 4mo

Applied to 25 Min Talk on MetaEthical.AI with Questions from Stuart Armstrong by June Ku at 5mo

Applied to RFC: Meta-ethical uncertainty in AGI alignment by MichaelA at 5mo

Applied to Another (outer) alignment failure story by Multicore at 5mo

Applied to My AGI Threat Model: Misaligned Model-Based RL Agent by Steve Byrnes at 6mo

Applied to Generalizing POWER to multi-agent games by Jacob Stavrianos at 6mo

Applied to A simple way to make GPT-3 follow instructions by Quintin Pope at 6mo

Applied to MIRI comments on Cotra's "Case for Aligning Narrowly Superhuman Models" by Rob Bensinger at 7mo

Applied to The case for aligning narrowly superhuman models by Ajeya Cotra at 7mo

Applied to Book review: "A Thousand Brains" by Jeff Hawkins by Steve Byrnes at 7mo