30:42

The Battle For The Future Of AI — Full Documentary

02:15:47

Owain Evans - AI Situational Awareness, LLM Out-of-Context Reasoning

18:33

The Economics of AGI Automation

18:11

AGI Takeoff By 2036

17:16

2040: The Year of Full AI Automation

14:23

AI Control: Humanity's Final Line Of Defense (Walkthrough)

17:06

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training (Walkthrough)

21:32

Anthropic Caught Their Backdoored Models (Walkthrough)

31:23

Anthropic Solved Interpretability Again? (Walkthrough)

36:40

Ethan Perez (Anthropic) - Bottom-Up Alignment Research

12:43

2024: The Year Of Artificial General Intelligence

01:42:49

Emil Wallner—Sora, Text-to-video, AGI optimism

52:32

Evan Hubinger (Anthropic)—Deception, Sleeper Agents, Responsible Scaling

01:40:17

Holly Elmore—Pausing Frontier AI Development

07:21

GPT-2 Teaches GPT-4: Weak-to-Strong Generalization

12:32

How to Catch an AI Liar

11:49

Anthropic Solved Interpretability?

18:59

We Beat The Strongest Go AI

04:54

Paul Christiano's Views on AI Doom (ft. Robert Miles)

02:05:31

Neel Nanda–Mechanistic Interpretability, Superposition, Grokking

02:54:30

Joscha Bach—Is AI Risk Real?

22:37

Erik Jones—Automatically Auditing Large Language Models

12:23

Dylan Patel—GPU Shortage, Nvidia, Semiconductor Supply Chain

10:40

Andi Peng—A Human-in-the-Loop Framework for Test-Time Policy Adaptation

08:18

Hailey Schoelkopf—Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling

06:08

Tomek Korbak—Pretraining Language Models with Human Preferences

06:46

Tim Dettmers—k-bit Inference Scaling Laws

01:54

Eric Wallace—Poisoning Language Models During Instruction Tuning

23:58

Tony Wang—Beating Superhuman Go AIs

24:54

David Bau—Editing Facts in GPT, Interpretability

20:11

Alexander Pan–Are AIs Machiavellian?

18:08

Vincent Weisser–Funding Alignment Research

01:17:22

Aran Komatsuzaki–Scaling, GPT-J

01:29:59

Curtis Huebner—AGI by 2028, 90% Doom

48:23

Eric Michaud—Scaling, Grokking, Quantum Interpretability

37:26

Daniel Filan–AXRP, LLMs, Interpretability

09:30

Existential Risk From AI Is Higher Than 10%—Change My Mind

43:12

Jesse Hoogland–AI Risk, Interpretability

04:25

Clarifying and predicting AGI

01:12:47

Alan Chan and Max Kaufmann–Model Evaluations, Timelines, Coordination

01:44:14

Breandan Considine–AI Timelines, Coding AI, Neuro Symbolic AI

31:11

Christoph Schuhmann–Open Source AI, Misuse, Existential risk

02:04:17

Simeon Campos–Short Timelines, AI Governance, Field Building

26:28

ML Street Talk–AI Existential Risk

10:00

ML Street Talk–Takeoff Speeds

02:35:10

Collin Burns–Making GPT-N Honest

01:52:27

Victoria Krakovna–AGI Ruin, Sharp Left Turn, Paradigms of AI Alignment

02:45:20

David Krueger—Coordination, AI Alignment, Academia

12:19

Scale Is All You Need: Change My Mind

23:48

Ethan Caballero–Broken Neural Scaling Laws

01:26:30

Irina Rish—AGI, Scaling, Alignment

02:04:41

Shahar Avin–AI Governance

01:41:15

Katja Grace—Slowing Down AI, Forecasting AI Risk

01:43:06

Markus Anderljung–Regulating Advanced AI

01:05:13

Alex Lawsen—Forecasting AI Progress

01:46:44

Robert Long–Artificial Sentience, Digital Minds

02:01:27

Ethan Perez–Inverse Scaling, Red Teaming

02:51:17

Robert Miles–Existential Risk from AI

02:57:20

Connor Leahy–EleutherAI, Conjecture

51:54

Ethan Caballero–Scale Is All You Need