AI Safety Fundamentals: Alignment
A podcast by BlueDot Impact
Categorie:
83 Episodio
-
Public by Default: How We Manage Information Visibility at Get on Board
Pubblicato: 12/5/2024 -
Writing, Briefly
Pubblicato: 12/5/2024 -
Being the (Pareto) Best in the World
Pubblicato: 4/5/2024 -
How to Succeed as an Early-Stage Researcher: The “Lean Startup” Approach
Pubblicato: 23/4/2024 -
Become a Person who Actually Does Things
Pubblicato: 17/4/2024 -
Planning a High-Impact Career: A Summary of Everything You Need to Know in 7 Points
Pubblicato: 16/4/2024 -
Working in AI Alignment
Pubblicato: 14/4/2024 -
Computing Power and the Governance of AI
Pubblicato: 7/4/2024 -
Emerging Processes for Frontier AI Safety
Pubblicato: 7/4/2024 -
Challenges in Evaluating AI Systems
Pubblicato: 7/4/2024 -
AI Control: Improving Safety Despite Intentional Subversion
Pubblicato: 7/4/2024 -
AI Watermarking Won’t Curb Disinformation
Pubblicato: 7/4/2024 -
Interpretability in the Wild: A Circuit for Indirect Object Identification in GPT-2 Small
Pubblicato: 1/4/2024 -
Towards Monosemanticity: Decomposing Language Models With Dictionary Learning
Pubblicato: 31/3/2024 -
Zoom In: An Introduction to Circuits
Pubblicato: 31/3/2024 -
Weak-To-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
Pubblicato: 26/3/2024 -
Can We Scale Human Feedback for Complex AI Tasks?
Pubblicato: 26/3/2024 -
Machine Learning for Humans: Supervised Learning
Pubblicato: 13/5/2023 -
Four Background Claims
Pubblicato: 13/5/2023 -
Biological Anchors: A Trick That Might Or Might Not Work
Pubblicato: 13/5/2023
Listen to resources from the AI Safety Fundamentals: Alignment course!https://aisafetyfundamentals.com/alignment