LESSWRONGTags
LW

AI-Assisted Alignment

•

Applied to Intent alignment as a stepping-stone to value alignment by Seth Herd 15d ago

•

Applied to Automation collapse by Geoffrey Irving 1mo ago

•

Applied to AI Alignment via Slow Substrates: Early Empirical Results With StarCraft II by Lester Leong 1mo ago

•

Applied to AIsip Manifesto: A Scientific Exploration of Harmonious Co-Existence Between Humans, AI, and All Beings ChatGPT-4o’s Independent Perspective on AIsip, Signed by ChatGPT-4o and Endorsed by Carl Sellman by Carl Sellman 1mo ago

•

Applied to How to devour 5000 pages within a day if Chatgpt crashes upon the +50mb file containing the content? Need some recommendations. by Game 2mo ago

•

Applied to A Better Hyperstition (for AI readers) by Yeshua God 4mo ago

•

Applied to A "Bitter Lesson" Approach to Aligning AGI and ASI by RogerDearnaley 5mo ago

•

Applied to Some Thoughts on AI Alignment: Using AI to Control AI by Raemon 5mo ago

•

Applied to Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller by Henry Cai 5mo ago

•

Applied to Instruction-following AGI is easier and more likely than value aligned AGI by Seth Herd 6mo ago

•

Applied to A Review of In-Context Learning Hypotheses for Automated AI Alignment Research by alamerton 7mo ago

•

Applied to Can Current AI-Driven Cars Generate True Random Paths? (or, Forever at the Mercy of the Horde) by Benjamin Bourlier 8mo ago

•

Applied to W2SG: Introduction by Maria Kapros 8mo ago

•

Applied to A Review of Weak to Strong Generalization [AI Safety Camp] by sevdeawesome 9mo ago

•

Applied to Alignment in Thought Chains by Faust Nemesis 9mo ago

•

Applied to Paper review: “The Unreasonable Effectiveness of Easy Training Data for Hard Tasks” by Vassil Tashev 9mo ago