Refine

Applied to What I Learned Running Refine by adamShimi 2y ago

Applied to A newcomer’s guide to the technical AI safety field by zeshen 2y ago

Applied to Embedding safety in ML development by zeshen 2y ago

Applied to Refine: what helped me write more? by zeshen 2y ago

Applied to Cataloguing Priors in Theory and Practice by Paul Bricman 2y ago

Applied to confusion about alignment requirements by adamShimi 2y ago

Applied to my current outlook on AI risk mitigation by Tamsin Leake 2y ago

Applied to Boolean Primitives for Coupled Optimizers by Paul Bricman 2y ago

Applied to Epistemic Artefacts of (conceptual) AI alignment research by Andrea_Miotti 2y ago

Applied to (Structural) Stability of Coupled Optimizers by Paul Bricman 2y ago

Applied to My Thoughts on the ML Safety Course by zeshen 2y ago

Applied to Summary of ML Safety Course by zeshen 2y ago

Applied to Interlude: But Who Optimizes The Optimizer? by Paul Bricman 2y ago

Applied to Representational Tethers: Tying AI Latents To Human Ones by adamShimi 2y ago

Applied to Refine's Third Blog Post Day/Week by adamShimi 2y ago

Applied to Refine Blogpost Day #3: The shortforms I did write by Ruby 2y ago

Applied to ordering capability thresholds by Tamsin Leake 2y ago

Applied to Levels of goals and alignment by zeshen 2y ago

Applied to Ideological Inference Engines: Making Deontology Differentiable* by Paul Bricman 2y ago

Applied to Oversight Leagues: The Training Game as a Feature by Paul Bricman 2y ago