Yuandong Tian: Inside-out interpretability: training dynamics in multi-layer transformer

  Рет қаралды 234

Berkeley RDI Center on Decentralization & AI

Berkeley RDI Center on Decentralization & AI

Күн бұрын

Пікірлер
Bo Li: Benchmarks and evals, safety vs. capabilities, machine ethics
1:19:14
Berkeley RDI Center on Decentralization & AI
Рет қаралды 184
Lazy days…
00:24
Anwar Jibawi
Рет қаралды 9 МЛН
Что-что Мурсдей говорит? 💭 #симбочка #симба #мурсдей
00:19
Nicholas Carlini: The security of LLMs
1:16:58
Berkeley RDI Center on Decentralization & AI
Рет қаралды 359
Can Intel survive the valley of death?
22:26
TechAltar
Рет қаралды 376 М.
AMD's CEO Wants to Chip Away at Nvidia's Lead | The Circuit with Emily Chang
24:02
Do Aliens Exist? Professor Brian Cox Answers Your Questions | Honesty Box
32:09
How AI Cracked the Protein Folding Code and Won a Nobel Prize
22:20
Quanta Magazine
Рет қаралды 303 М.
Visualizing transformers and attention | Talk for TNG Big Tech Day '24
57:45
How do Graphics Cards Work?  Exploring GPU Architecture
28:30
Branch Education
Рет қаралды 2,2 МЛН
Martin Wattenberg: Models within models - how do LLMs represent the world?
1:15:02
Berkeley RDI Center on Decentralization & AI
Рет қаралды 839
Lazy days…
00:24
Anwar Jibawi
Рет қаралды 9 МЛН