AbstractAlgorithms
Home/Learn/Ai Safety
Topic

Ai Safety

Learn Ai Safety as a connected topic across chapters, concepts, simulations, and interview reasoning.

10 Concepts1 Articles12 min
Start LearningAdd to Learning

Overview

Learn Ai Safety as a connected topic across chapters, concepts, simulations, and interview reasoning.

How this topic helps

Ai
Alignment
Llm
Reinforcement Learning

Learning Path in this Topic

Series that contain articles from Ai Safety. Select a path to filter the article list.

Articles

1 matched article

Article 1RLHF in Practice: From Human Preferences to Better LLM PoliciesTLDR: Reinforcement Learning from Human Feedback (RLHF) helps align language models with human preferences after pretraining and SFT. The typical pipeline is: collect preference comparisons, train a r12 min