AI

Applied to Causality, Transformative AI and alignment - part I by Marius Hobbhahn at 2d

Applied to Arguments about Highly Reliable Agent Designs as a Useful Path to Artificial Intelligence Safety by Issa Rice at 2d

Applied to Could anyone kindly answer interview questions about AI for my school research project? by Curious_Cruiser at 3d

Applied to Aligned AI Needs Slack by Ruben Bloom at 3d

Applied to ELK First Round Contest Winners by Ruben Bloom at 3d

Applied to [Intro to brain-like-AGI safety] 1. What's the problem & Why work on it now? by Steve Byrnes at 3d

Applied to Search Is All You Need by Raymond Arnold at 3d

Applied to ML Systems Will Have Weird Failure Modes by Raymond Arnold at 3d

Applied to How feasible/costly would it be to train a very large AI model on distributed clusters of GPUs? by Anonymous at 4d

Applied to Is AI Alignment a pseudoscience? by Luna Rimar at 6d

Applied to A one-question Turing test for GPT-3 by Ruben Bloom at 7d

Applied to Alignment Problems All the Way Down by peterbarnett at 8d

Applied to [AN #171]: Disagreements between alignment "optimists" and "pessimists" by Raymond Arnold at 8d

Applied to Sharing Powerful AI Models by Ruben Bloom at 8d

Applied to What's Up With Confusingly Pervasive Consequentialism? by Tobias D. at 9d

Applied to Emotions = Reward Functions by jpyykko at 9d

Applied to Estimating training compute of Deep Learning models by Ruben Bloom at 9d

Applied to Anchor Weights for ML by Ruben Bloom at 9d

Applied to Action: Help expand funding for AI Safety by coordinating on NSF response by Evan R. Murphy at 10d