Alineación deliberativa
24:04
Alinhamento falso em grandes modelos de linguagem
16:00
RE-Bench: medindo agentes de IA em P&D de IA versus especialistas humanos
15:49
What does AI believe is true?
25:31
Is Chain of Thought faithful?
27:14
Transformers (how LLMs work) explained visually | DL5
36:47
The Next Frontier: Sam Altman on the Future of A.I. and Society
19:35
Anthropic - AI sleeper agents?
16:02