Sharp Left Turn

Applied to A simple treacherous turn demonstration by nikola 5mo ago

Applied to [Interview w/ Quintin Pope] Evolution, values, and AI Safety by RobertM 6mo ago

Applied to Evolution Solved Alignment (what sharp left turn?) by Tobias D. 6mo ago

Applied to We don't understand what happened with culture enough by Jan_Kulveit 6mo ago

Applied to A few Alignment questions: utility optimizers, SLT, sharp left turn and identifiability by jacobjacob 7mo ago

Applied to The Sharp Right Turn: sudden deceptive alignment as a convergent goal by avturchin 10mo ago

Applied to Evolution provides no evidence for the sharp left turn by Quintin Pope 1y ago

Applied to A smart enough LLM might be deadly simply if you run it for long enough by Mikhail Samin 1y ago

Applied to Reframing inner alignment by Victoria Krakovna 1y ago

Applied to Victoria Krakovna on AGI Ruin, The Sharp Left Turn and Paradigms of AI Alignment by Raymond Arnold 1y ago

Applied to How is the "sharp left turn defined"? by Raymond Arnold 1y ago

Applied to Refining the Sharp Left Turn threat model, part 2: applying alignment techniques by Victoria Krakovna 1y ago

Applied to A caveat to the Orthogonality Thesis by Wuschel Schulz 1y ago

Applied to Disentangling inner alignment failures by Erik Jenner 2y ago

Applied to Smoke without fire is scary by Adam Jermyn 2y ago

Applied to It matters when the first sharp left turn happens by Adam Jermyn 2y ago

Applied to Goal Alignment Is Robust To the Sharp Left Turn by Multicore 2y ago

Applied to We may be able to see sharp left turns coming by Multicore 2y ago

Applied to A central AI alignment problem: capabilities generalization, and the sharp left turn by Multicore 2y ago