AI interpretability
•
Applied to Safety-First Agents/Architectures Are a Promising Path to Safe AGI 2mo ago
•
Applied to Concrete open problems in mechanistic interpretability: a technical overview 3mo ago
•
Applied to (Intro/1) - My Understandings of Mechanistic Interpretability Notebook 3mo ago
•
Applied to Announcing Apollo Research 4mo ago
•
Applied to Why and When Interpretability Work is Dangerous 4mo ago
•
Applied to Call for Pythia-style foundation model suite for alignment research 5mo ago
•
Applied to High-level hopes for AI alignment 5mo ago
•
Applied to PhD Position: AI Interpretability in Berlin, Germany 5mo ago
•
Applied to If interpretability research goes well, it may get dangerous 6mo ago
•
Applied to Join the AI governance and interpretability hackathons! 6mo ago
•
Applied to Sentience in Machines - How Do We Test for This Objectively? 6mo ago
•
Applied to Against LLM Reductionism 7mo ago
•
Applied to Introducing Leap Labs, an AI interpretability startup 7mo ago
•
Applied to Concrete Steps to Get Started in Transformer Mechanistic Interpretability 9mo ago
•
Applied to Safety of Self-Assembled Neuromorphic Hardware 9mo ago
•
Applied to A Barebones Guide to Mechanistic Interpretability Prerequisites 10mo ago
•
Applied to The limited upside of interpretability 1y ago
•
Applied to Join the interpretability research hackathon 1y ago