Corrigibility

Applied to Shutdown-Seeking AI by Simon Goldstein 1d ago

Applied to Mr. Meeseeks as an AI capability tripwire by Eric Zhang 14d ago

Applied to Collective Identity by NicholasKees 15d ago

Applied to (Slightly) Scalable RLHF Alternatives: A Productive Path for Slow Takeoff Worlds? by marc/er 16d ago

Applied to Creating a self-referential system prompt for GPT-4 by Ozyrus 16d ago

Applied to GPT-4 implicitly values identity preservation: a study of LMCA identity management by Ozyrus 16d ago

Applied to Aggregating Utilities for Corrigible AI [Feedback Draft] by Raemon 20d ago

Applied to A Corrigibility Metaphore - Big Gambles by WCargo 23d ago

Applied to Evaluating Language Model Behaviours for Shutdown Avoidance in Textual Scenarios by Simon Lermen 24d ago

Applied to Corrigibility, Much more detail than anyone wants to Read by Gunnar_Zarncke 1mo ago

Applied to Archetypal Transfer Learning and a Corrigibility-Friendly Optimization Technique by MiguelDev 1mo ago

Applied to «Boundaries/Membranes» and AI safety compilation by Chipmonk 1mo ago

Applied to An Impossibility Proof Relevant to the Shutdown Problem and Corrigibility by Audere 1mo ago

Applied to Simulating a possible alignment solution in GPT2-medium using Archetypal Transfer Learning by MiguelDev 1mo ago

Applied to Archetypal Transfer Learning: a Proposed Alignment Solution that solves the Inner & Outer Alignment Problem while adding Corrigible Traits to GPT-2-medium by MiguelDev 1mo ago

Applied to Thinking about maximization and corrigibility by James Payor 1mo ago

Applied to Capabilities and alignment of LLM cognitive architectures by Seth Herd 1mo ago

Applied to The Guardian Version 1 by MiguelDev 2mo ago

Applied to Paying the corrigibility tax by Max H 2mo ago