AI Risk

Applied to [Review] "The Alignment Problem" by Brian Christian by Lsusr at 2d

Applied to Investigating AI Takeover Scenarios by Samuel Dylan Martin at 6d

Applied to How truthful is GPT-3? A benchmark for language models by Owain Evans at 6d

Applied to The alignment problem in different capability regimes by Multicore at 11d

Applied to Distinguishing AI takeover scenarios by Sam Clarke at 13d

Applied to Bayeswatch 7: Wildfire by Lsusr at 14d

Applied to Conditional on the first AGI being aligned correctly, is a good outcome even still likely? by iamthouthouarti at 15d

Applied to Why the technological singularity by AGI may never happen by Ruben Bloom at 18d

Applied to The Governance Problem and the "Pretty Good" X-Risk by Zachary Stein-Perlman at 23d

Applied to What are good alignment conference papers? by Adam Shimi at 24d

Applied to Could you have stopped Chernobyl? by Carlos Ramirez at 1mo

Applied to A gentle apocalypse by Pavel Chvykov at 1mo

Applied to Approaches to gradient hacking by Adam Shimi at 1mo

Applied to Mauhn Releases AI Safety Documentation by Berg Severens at 3mo

Applied to What are some claims or opinions about multi-multi delegation you've seen in the memeplex that you think deserve scrutiny? by Quinn Dougherty at 3mo

Applied to Sam Altman and Ezra Klein on the AI Revolution by Zack M. Davis at 3mo

Applied to Alex Turner's Research, Comprehensive Information Gathering by Alex Turner at 3mo

Applied to Environmental Structure Can Cause Instrumental Convergence by Alex Turner at 3mo