Training AI Without Writing A Reward Function, with Reward Modelling
10:22
AI That Doesn't Try Too Hard - Maximizers and Satisficers
9:40
9 Examples of Specification Gaming
0:40
[프로미스나인] 고삐풀린 막둥이 #프로미스나인 #fromis_9 #백지헌 #막내 #라이브 #shorts
13:03
Intelligence and Stupidity: The Orthogonality Thesis
16:00
AI Safety Gym - Computerphile
16:29
10 Reasons to Ignore AI Safety
15:38
A Response to Steven Pinker on AI
18:05