Inner Alignment

Applied to Ways to think about alignment by Abhimanyu Pallavi Sudhir 24d ago

Applied to Why humans won't control superhuman AIs. by Spiritus Dei 1mo ago

Applied to What constitutes an infohazard? by K1r4d4rk.v1 1mo ago

Applied to HDBSCAN is Surprisingly Effective at Finding Interpretable Clusters of the SAE Decoder Matrix by Jaehyuk Lim 2mo ago

Applied to Deception and Jailbreak Sequence: 2. Iterative Refinement Stages of Jailbreaks in LLM by Winnie Yang 3mo ago

Applied to AI Rights for Human Safety by Simon Goldstein 4mo ago

Applied to Pacing Outside the Box: RNNs Learn to Plan in Sokoban by Adrià Garriga-alonso 4mo ago

Applied to A more systematic case for inner misalignment by Ruby 4mo ago

Applied to Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent by Karolis Jucys 4mo ago

Applied to A simple case for extreme inner misalignment by quila 4mo ago

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

Applied to Language for Goal Misgeneralization: Some Formalisms from my MSc Thesis by Giulio 5mo ago

Applied to Demystifying "Alignment" through a Comic by milanrosko 5mo ago

Applied to Finding Backward Chaining Circuits in Transformers Trained on Tree Search by abhayesian 6mo ago

Applied to minutes from a human-alignment meeting by bhauth 6mo ago