37:57

BlackboxNLP

Catherine Olsson - Induction Heads

1,639 回視聴 - 2 年前

3:42:37

Machine Learning Street Talk

NEURAL NETWORKS ARE WEIRD! - Neel Nanda (DeepMind)

103,043 回視聴 - 5 か月前

27:14

3Blue1Brown

Transformers (how LLMs work) explained visually | DL5

6,355,606 回視聴 - 1 年前

8:19:57

Nathan Lile

Mechanistic Interpretability Workshop 2024 at ICML - Full Recording

212 回視聴 - 8 か月前

31:34

CCP4

Integrating Machine Learning Frameworks in Scientific Workflows - Piero Gasparotto

19 回視聴 - 8 日前

1:23:57

Berkeley RDI Center on Decentralization & AI

David Bau: Interpretability and model editing

570 回視聴 - 8 か月前

39:07

Yakka Analytics

Your First Power BI Dashboard: A Beginner’s Guide to Data Visualisation

1 回視聴 - 7 時間前

1:32:50

Stevan Harnad

LLM Understanding: 15 J. TENENBAUM "Word Models to World Models: Probabilistic Language of Thought"

2,241 回視聴 - 11 か月前

1:26:48

AI Safety Talks

Concrete Open Problems in Mechanistic Interpretability: Neel Nanda at SERI MATS

4,427 回視聴 - 2 年前

45:01

Internet2

Cracking Open the Mystery of Large Scale AI

108 回視聴 - 1 か月前

27:31

IBM Technology

Cybersecurity Architecture: Networks

280,618 回視聴 - 1 年前

25:48

BBC World Service

What do tech pioneers think about the AI revolution? - BBC World Service

1,638,372 回視聴 - 9 か月前

1:00:15

Umar Jamil

ML Interpretability: feature visualization, adversarial example, interp. for language models

10,144 回視聴 - 1 年前

1:23:57

UC Berkeley EECS

David Bau: Interpretability and model editing

2,153 回視聴 - 10 か月前

19:23

Symposia at CSAIL

CSAIL 20/60 Anniversary Celebration, Prof. David Bau - Big Questions and Terrifying Tea

359 回視聴 - 1 年前

1:01:40

Future of Life Institute

Neel Nanda on Avoiding an AI Catastrophe with Mechanistic Interpretability

3,046 回視聴 - 2 年前

55:27

Google TechTalks

Open Problems in Mechanistic Interpretability: A Whirlwind Tour

6,118 回視聴 - 1 年前

36:29

Black Hat

Compromising LLMs: The Advent of AI Malware

7,976 回視聴 - 1 年前