Problem Areas in Physics and AI Safety | Apart Research

Apart Research is an independent research organization focusing on AI safety. We accelerate AI safety research through mentorship, collaborations, and research sprints

Problem Areas in Physics and AI Safety | Apart Research Problem Areas in Physics and AI Safety We outline five key problem areas in AI safety for the AI Safety x Physics hackathon. Ari Brill Researcher Lauren Greenspan Researcher Title Although there is a lot of good physics for AI literature out there, we take a predominantly ‘problem first’ approach. This is to avoid restricting solutions to specific physics fields, methods, and tools. We’re excited to reframe these old perspectives and find new ones! To guide you in getting started, we’ve developed the following problem space for AI safety,

related reading

• Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
• Statistical Physics for Ambitious Interpretability: A Workshop Retrospective — LessWronglesswrong.com
• Vibe physics: The AI grad student \ Anthropicanthropic.com
• Home | Physics Of Learningphysicsoflearning.org
• How To Become A Mechanistic Interpretability Researcher — AI Alignment Forumalignmentforum.org
• AI Safety: A Short FAQ for Mathematiciansalkjash.github.io
• Explaining the Apart Research Fellowships | Apart Researchapartresearch.com
• Renormalization Roadmap — LessWronglesswrong.com
• Simplexsimplexaisafety.com
• Ten AI safety projects I'd like people to work onthirdthing.ai
• Simplex - building our research team | Manifundmanifund.org
• Want to upskill in technical AI safety? Here are 67 useful resources | 80,000 Hours80000hours.org