✳flâneur — a map of the web's best reading
A guide to Iterated Amplification & Debate - AI Alignment Forum
alignmentforum.org · 4,858 words · saved by 1 readers
This post is about two proposals for aligning AI systems in a scalable way: …
x A guide to Iterated Amplification & Debate — AI Alignment Forum Factored Cognition Debate (AI safety technique) Iterated Amplification Factored Cognition AI Risk Humans consulting HCH AI Frontpage 28 A guide to Iterated Amplification & Debate by Rafael Harth 15th Nov 2020 18 min read 15 28 This post is about two proposals for aligning AI systems in a scalable way: Iterated Distillation and Amplification (often just called 'Iterated Amplification'), or IDA for short, [1] is a proposal by Paul Christiano . Debate is an IDA-inspired proposal by Geoffrey Irving . This post is written to be as ea
Explore this link on the map →related reading
- Mediumai-alignment.com
- AI 2027ai-2027.com
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- [1805.00899] AI safety via debatear5iv.labs.arxiv.org
- A positive case for how we might succeed at prosaic AI alignment — AI Alignment Forumalignmentforum.org
- An alignment safety case sketch based on debate — LessWronglesswrong.com
- An overview of 11 proposals for building safe advanced AI — AI Alignment Forumalignmentforum.org
- AGI Ruin: A List of Lethalities — LessWronglesswrong.com
- AI 2027ai-2027.com
- [1805.00899] AI safety via debatearxiv.org
- The Iliad Intensive Course Materials — LessWronglesswrong.com
- An AI alignment research agenda based on asymmetric debate and monitoring. — LessWronglesswrong.com