Outer Alignment

Applied to Conditioning, Prompts, and Fine-Tuning by Adam Jermyn at 10h

Applied to Human Mimicry Mainly Works When We’re Already Close by Raymond Arnold at 12h

Applied to What Makes an Idea Understandable? On Architecturally and Culturally Natural Ideas. by NickyP at 2d

Applied to Shard Theory: An Overview by Kaj Sotala at 7d

Applied to Externalized reasoning oversight: a research direction for language model alignment by tamera at 15d

Applied to Reward is not the optimization target by Quintin Pope at 24d

Applied to Conditioning Generative Models with Restrictions by Adam Jermyn at 1mo

Applied to Our Existing Solutions to AGI Alignment (semi-safe) by Michael Soareverix at 1mo

Applied to Conditioning Generative Models for Alignment by Arun Jose at 1mo

Applied to Alignment as Game Design by Raymond Arnold at 1mo

Applied to Three Minimum Pivotal Acts Possible by Narrow AI by Michael Soareverix at 1mo

Applied to Making it harder for an AGI to "trick" us, with STVs by Tor Økland Barstad at 1mo

Applied to Research Notes: What are we aligning for? by Shoshannah Tekofsky at 1mo

Applied to Outer vs inner misalignment: three framings by Raymond Arnold at 1mo

Applied to Naive Hypotheses on AI Alignment by Kaj Sotala at 2mo

Applied to Announcing the Inverse Scaling Prize ($250k Prize Pool) by Ethan Perez at 2mo

Applied to Getting from an unaligned AGI to an aligned AGI? by Tor Økland Barstad at 2mo

Applied to Investigating causal understanding in LLMs by Marius Hobbhahn at 2mo