Research Agendas

Applied to Research agenda: Formalizing abstractions of computations by Erik Jenner at 5d

Applied to Interpretability’s Alignment-Solving Potential: Analysis of 7 Scenarios by Evan R. Murphy at 5d

Applied to Selection Theorems: A Program For Understanding Agents by DragonGod at 8d

Applied to The AI Control Problem in a wider intellectual context by philosophybear at 25d

Applied to World-Model Interpretability Is All We Need by Thane Ruthenis at 1mo

Applied to Trying to isolate objectives: approaches toward high-level interpretability by Jozdien at 1mo

Applied to Research ideas (AI Interpretability & Neurosciences) for a 2-months project by flux at 1mo

Applied to Announcing: The Independent AI Safety Registry by Shoshannah Tekofsky at 1mo

Applied to An overview of some promising work by junior alignment researchers by Akash at 1mo

Applied to Towards Hodge-podge Alignment by Cleo Nardo at 2mo

Applied to My AGI safety research—2022 review, ’23 plans by Steven Byrnes at 2mo

Applied to Theories of impact for Science of Deep Learning by Marius Hobbhahn at 2mo

Applied to My summary of “Pragmatic AI Safety” by Eleni Angelou at 3mo

Applied to All life's helpers' beliefs by Tehdastehdas at 3mo

Applied to Apply to the Redwood Research Mechanistic Interpretability Experiment (REMIX), a research program in Berkeley by Rudi C at 3mo

Applied to AI researchers announce NeuroAI agenda by Cameron Berg at 3mo

Applied to Distilled Representations Research Agenda by Ruby at 4mo