AI

Applied to The AGI needs to be honest by rokosbasilisk at 38m

Applied to Memetic hazards of AGI architecture posts by Ruben Bloom at 2h

Applied to We're Redwood Research, we do applied alignment research, AMA by Multicore at 3h

Applied to NLP Position Paper: When Combatting Hype, Proceed with Caution by Ruben Bloom at 21h

Applied to Classical symbol grounding and causal graphs by Ruben Bloom at 2d

Applied to Commentary on “AGI Safety From First Principles by Richard Ngo, September 2020” by Ruben Bloom at 2d

Applied to Compute Governance and Conclusions - Transformative AI and Compute [3/4] by Ruben Bloom at 2d

Applied to [Proposal] Method of locating useful subnets in large models by Ruben Bloom at 3d

Applied to Bayeswatch 13: Spaceship by Lsusr at 4d

Applied to Modeling Risks From Learned Optimization by Issa Rice at 4d

Applied to On Solving Problems Before They Appear: The Weird Epistemologies of Alignment by Ruben Bloom at 5d

Applied to NVIDIA and Microsoft releases 530B parameter transformer model, Megatron-Turing NLG by Kaj Sotala at 5d

Applied to Good AI alignment online class? by Ruben Bloom at 6d

Applied to The evaluation function of an AI is not its aim by Ruben Bloom at 6d

Applied to The Extrapolation Problem by Ruben Bloom at 6d

Applied to Bayeswatch 12: The Singularity War by Lsusr at 7d

Applied to Intelligence or Evolution? by Ben Pace at 7d

Applied to Steelman arguments against the idea that AGI is inevitable and will arrive soon by Ruben Bloom at 7d