Why Would AI Want to do Bad Things? Instrumental Convergence Robert Miles AI Safety 10:36 6 years ago 247 381 Скачать Далее
Alignment Newsletter #107: The convergent instrumental subgoals of goal-directed agents Alignment Newsletter Podcast 14:12 3 years ago 9 Скачать Далее
J. Dmitri Gallow - AI Interpretability, Orthogonality, Instrumental Convergence & Divergence Science, Technology & the Future 23:42 4 months ago 236 Скачать Далее
Instrumental Convergence, Lacanian Topology, and the Automation of the Real Donald Kunze 13:29 10 months ago 587 Скачать Далее
Nick Bostrom's Warning: How Superintelligence Could End Humanity Low Budget AI 5:04 1 year ago 215 Скачать Далее
Lacan to the Limits: Instrumental Convergence and the Cut of Psychoanalysis Donald Kunze 47:57 11 months ago 1 432 Скачать Далее
The OTHER AI Alignment Problem: Mesa-Optimizers and Inner Alignment Robert Miles AI Safety 23:24 3 years ago 224 302 Скачать Далее
Elon Musk Laughs at the Idea of Getting a PhD... and Explains How to Actually Be Useful! Inspire Greatness 0:39 2 years ago 7 636 442 Скачать Далее
Alignment Newsletter #78: Formalizing power and instrumental convergence, and the end-of-year AI... Alignment Newsletter Podcast 18:04 3 years ago 31 Скачать Далее
Nick Bostrom Super-intelligence views on Artificial Intelligence (AI) LifeLongLearners 21:01 1 year ago 320 Скачать Далее
The Impossibility and Uncertainy of AGI Alignment (Paper Breakdown) Tunadorable 22:48 10 months ago 98 Скачать Далее
Safe Exploration: Concrete Problems in AI Safety Part 6 Robert Miles AI Safety 13:46 5 years ago 96 272 Скачать Далее
ROBERT MILES - "There is a good chance this kills everyone" Machine Learning Street Talk 2:01:55 1 year ago 68 839 Скачать Далее