10:36Why Would AI Want to do Bad Things? Instrumental ConvergenceRobert Miles AI Safety 274K views · 6 HN recommenders · 2019–2023
13:03Intelligence and Stupidity: The Orthogonality ThesisRobert Miles AI Safety 711K views · 6 HN recommenders · 2022–2026
15:27Why Not Just: Think of AGI Like a Corporation?Robert Miles AI Safety 163K views · 5 HN recommenders · 2020–2023
13:44Is AI Safety a Pascal's Mugging?Robert Miles AI Safety 388K views · 3 HN recommenders · 2019–2026
17:52Training AI Without Writing A Reward Function, with Reward ModellingRobert Miles AI Safety 259K views · 3 HN recommenders · 2019–2023
9:33Avoiding Negative Side Effects: Concrete Problems in AI Safety part 1Robert Miles AI Safety 161K views · 2 HN recommenders · 2018–2023
11:47We Were Right! Real Inner MisalignmentRobert Miles AI Safety 271K views · 1 HN recommender · 2023
