As of April 2023, there is a lot of new interest in the field of AI Alignment. However, this repo is unmaintained since I gave up hope about solving alignment on-time as a species - almost three years ago.
Maybe AI Safety Support is one of the definitive resources right now.
I will, however, accept PRs on this repo.
Welcome to Awesome-AI Alignment - a curated list of awesome resources for getting-into and staying-in-touch with the research in AI Alignment.
AI Alignment is also known as AI Safety, Beneficial AI, Human-aligned AI, Friendly AI etc.
If you are a newcomer to this field, start with the Crash Course below.
Pull requests are welcome.
- Awesome Artificial Intelligence Alignment
- Can we build AI without losing control over it? - Sam Harris
- What happens when our computers get smarter than we are? - Nick Bostrom
- WaitButWhy on AI Safety: Part 1 and Part 2
- A Reply by Luke Muehlhauser correcting a few things
- Superintelligence: Paths, Dangers, Strategies by Nick Bostrom
- Life 3.0 by Max Tegmark
- Artificial Intelligence Safety and Security by Roman Yampolskiy (Editor)
- CS 294-149: Safety and Control for Artificial General Intelligence (Fall 2018) by Andrew Critch and Stuart Russel [UC Berkeley]
- CS 521: Seminar on AI Safety by Dorsa Sadigh [Stanford]
- Paul Christiano’s Agenda summarised by Ajeya Cotra
- The Learning-Theoretic AI Alignment Research Agenda by Vadim Kosoy
- MIRI Machine Learning Agenda by Jessica Taylor and Eliezer Yudkowsky and Patrick LaVictoire and Andrew Critch
- MIRI Agent Foundations Agenda by Nate Soares and Benya Fallenstein
- Concrete Problems in AI Safety by Dario Amodei, Chris Olah, Jacob Steinhardt, Paul Christiano, John Schulman, Dan Mané
- DeepMind Scalable Agent Alignment Agenda by Jan Leike, David Krueger, Tom Everitt, Miljan Martic, Vishal Maini, and Shane Legg
- MIRI 2018 Research Directions by Nate Soares
- Integrative Biological Simulation, Neuropsychology, and AI Safety by Gopal P. Sarma, Adam Safron, and Nick J. Hay
- Reframing Superintelligence: Comprehensive AI Services as General Intelligence by Eric Drexler
- AGI Safety Literature Review by Tom Everitt, Gary Lea, Marcus Hutter
- Towards Safe Artificial General Intelligence - Tom Everitt’s PhD Thesis
- 2018 AI Alignment Literature Review and Charity Comparison by Larks
- FLI AI Policy Resources
- An Overview of Technical AI Alignment with Rohin Shah
- AI Alignment Research Overview by Jacob Steinhardt
- Can we build AI without losing control over it? - Sam Harris (2016)
- What happens when our computers get smarter than we are? - Nick Bostrom (2014)
- 3 principles for creating safer AI - Stuart Russell (2017)
- How to get empowered, not overpowered, by AI - Max Tegmark (2018)
- Risks of Artificial Intelligence by Johannes Heidecke
- Embedded Agency by Scott Garrabrant and Abram Demski
- Value Learning Sequence by Rohin Shah et al.
- Future of Life Institute
- Future of Humanity Institute
- Machine Intelligence Research Institute
- Ought
- OpenAI
- DeepMind Safety Team
- Center for Human-Compatible AI
- Nick Bostrom on *This Week in Machine Learning & AI*
- Eliezer Yudkowsky on Waking Up With Sam Harris
- Stuart Russel on *Waking Up With Sam Harris*
- AI Alignment Podcast by Lucas Perry [Future of Life Institute]
- 80000hours Podcast by Rob Wiblin
- Alignment Newsletter by Rohin Shah