Utility Functions

Applied to Notable runaway-optimiser-like LLM failure modes on Biologically and Economically aligned AI safety benchmarks for LLMs with simplified observation format by Roland Pihlakas 1mo ago

Applied to Toward a Mathematical Definition of Rationality in Multi-Agent Systems by nekofugu 2mo ago

Applied to Atlas: Stress-Testing ASI Value Learning Through Grand Strategy Scenarios by NeilFox 2mo ago

Applied to Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs by Matrice Jacobine 2mo ago

Applied to Why modelling multi-objective homeostasis is essential for AI alignment (and how it helps with AI safety as well) by Roland Pihlakas 4mo ago

Applied to Building AI safety benchmark environments on themes of universal human values by Roland Pihlakas 4mo ago

Applied to Is "VNM-agent" one of several options, for what minds can grow up into? by AnnaSalamon 4mo ago

Applied to Vegans need to eat just enough Meat - emperically evaluate the minimum ammount of meat that maximizes utility by Johannes C. Mayer 4mo ago

Applied to Better difference-making views by MichaelStJules 4mo ago

Applied to Expected Utility, Geometric Utility, and Other Equivalent Representations by StrivingForLegibility 5mo ago

Applied to Value/Utility: A History by Raemon 5mo ago

Applied to Valence Need Not Be Bounded; Utility Need Not Synthesize by Raemon 5mo ago

Applied to Galatea and the windup toy by Nicolas Villarreal 6mo ago

Applied to Resolving von Neumann-Morgenstern Inconsistent Preferences by niplav 6mo ago

Applied to Doing Nothing Utility Function by k64 7mo ago

Applied to Sequence overview: Welfare and moral weights by MichaelStJules 8mo ago