Myopia

Applied to "Corrigibility at some small length" by dath ilan by Christopher King 2mo ago

Applied to GPT-4 busted? Clear self-interest when summarizing articles about itself vs when article talks about Claude, LLaMA, or DALL·E 2 by Christopher King 2mo ago

Applied to A crazy hypothesis: GPT-4 already is agentic and is trying to take over the world! by Christopher King 2mo ago

Applied to GPT-4 aligning with acasual decision theory when instructed to play games, but includes a CDT explanation that's incorrect if they differ by Christopher King 2mo ago

Applied to Underspecification of Oracle AI by Evan R. Murphy 4mo ago

Applied to You can still fetch the coffee today if you're dead tomorrow by davidad 6mo ago

Applied to Steering Behaviour: Testing for (Non-)Myopia in Language Models by Evan R. Murphy 6mo ago

Applied to Simulators by Evan R. Murphy 7mo ago

Applied to Limiting an AGI's Context Temporally by Noosphere89 8mo ago

Applied to Generative, Episodic Objectives for Safe AI by Michael Glass 8mo ago

Applied to Laziness in AI by RobertM 9mo ago

Applied to Acceptability Verification: A Research Agenda by David Udell 1y ago

Applied to Interpretability’s Alignment-Solving Potential: Analysis of 7 Scenarios by Evan R. Murphy 1y ago

Applied to AI safety via market making by Evan R. Murphy 1y ago

Applied to How complex are myopic imitators? by Vivek Hebbar 1y ago

Applied to Evan Hubinger on Homogeneity in Takeoff Speeds, Learned Optimization and Interpretability by adamShimi 1y ago

Applied to Understanding and controlling auto-induced distributional shift by adamShimi 1y ago

Applied to Transforming myopic optimization to ordinary optimization - Do we want to seek convergence for myopic optimization problems? by tailcalled 1y ago

Applied to Ordinary People and Extraordinary Evil: A Report on the Beguilings of Evil by David Gross 2y ago