The Dark Matter of AI [Mechanistic Interpretability]

18:09
A genialidade do aumento de eficiência de 57X do DeepSeek [MLA]

22:48
Mechanistic Interpretability explained | Chris Olah and Lex Fridman

26:52
Learning Algorithm Of Biological Networks

18:02
AI Has a Fatal Flaw—And Nobody Can Fix It

24:01
ChatGPT is made from 100 million of these [The Perceptron]

17:38
The moment we stopped understanding AI [AlexNet]

15:13
Como o Resfriamento Magnético Está Quebrando Todas as Regras

22:57