ZARZA We are Zarza, the prestigious firm behind major projects in information technology.

AI Safety Fundamentals

AI Safety Fundamentals

Por: BlueDot Impact

Listen to resources from the AI Safety Fundamentals courses!https://aisafetyfundamentals.com/

173 episodios disponibles

Latest episodes of the podcast AI Safety Fundamentals

Mostrando página 3 de 9

AI Safety via Debate 04/01/2025

Least-To-Most Prompting Enables Complex Reasoning in Large Language Models 04/01/2025

Summarizing Books With Human Feedback 04/01/2025

Supervising Strong Learners by Amplifying Weak Experts 04/01/2025

Measuring Progress on Scalable Oversight for Large Language Models 04/01/2025

Is Power-Seeking AI an Existential Risk? 04/01/2025

Yudkowsky Contra Christiano on AI Takeoff Speeds 04/01/2025

Why AI Alignment Could Be Hard With Modern Deep Learning 04/01/2025

AGI Ruin: A List of Lethalities 04/01/2025

Where I Agree and Disagree with Eliezer 04/01/2025

ML Systems Will Have Weird Failure Modes 04/01/2025

Thought Experiments Provide a Third Anchor 04/01/2025

Goal Misgeneralisation: Why Correct Specifications Aren’t Enough for Correct Goals 04/01/2025

Deceptively Aligned Mesa-Optimizers: It’s Not Funny if I Have to Explain It 04/01/2025

What Failure Looks Like 04/01/2025

Learning From Human Preferences 04/01/2025

Specification Gaming: The Flip Side of AI Ingenuity 04/01/2025

Superintelligence: Instrumental Convergence 04/01/2025

The Easy Goal Inference Problem Is Still Hard 04/01/2025

The Alignment Problem From a Deep Learning Perspective 04/01/2025

« Primera ‹ Anterior 1 2 3 4 5 ... 9 Siguiente › Última »