Resource Library

by Ray Kurzweil

A landmark book exploring the coming merging of humans and machines, and the exponential growth of technology leading to the Singularity.

by Nick Bostrom

A foundational work examining the potential paths to machine superintelligence and the existential risks it poses.

by AI Safety Fundamentals Team

Comprehensive introduction to AGI safety concepts and core readings for newcomers to the field.

by Amodei et al.

Identifies practical safety problems that need to be solved before deploying AI systems in the real world.

by Lucas Perry

Weekly podcast featuring conversations with researchers working on AI alignment and existential risk.

by Hubinger et al.

Explores the dangers of mesa-optimization and inner alignment problems in machine learning systems.

by Robert Miles

Accessible video series explaining AI safety concepts, alignment problems, and existential risk.

by Nick Bostrom & Eliezer Yudkowsky

Philosophical examination of the ethical considerations surrounding artificial intelligence development.

by David Chalmers

Explores the hard problem of consciousness in relation to artificial intelligence and machine sentience.

by Stuart Russell

Proposes a new framework for building AI systems aligned with human values and preferences.

by Vaswani et al.

The groundbreaking paper introducing the Transformer architecture that revolutionized deep learning.

by Ian Goodfellow, Yoshua Bengio, Aaron Courville

Comprehensive textbook covering the mathematical foundations and practical implementations of deep learning.

by Kaplan et al.

Empirical study of how language model performance scales with model size, dataset size, and compute.

by Brundage et al.

Forecasts potential security threats from malicious uses of AI and proposes policy responses.

by Michael Horowitz

Analyzes the strategic implications of AI for national security and international relations.

by GovAI

Discussions with experts on AI governance, policy, and strategy for managing transformative AI.

by Brian Christian

Explores how to align machine values with human values as AI systems become more powerful.

by Christiano et al.

Introduces reinforcement learning from human feedback, a key technique for AI alignment.

by ARC Theory Team

Proposes methods for extracting truthful information from AI systems even when they have incentives to deceive.

by LessWrong Community

Online forum for technical AI alignment research discussion and collaboration.