Emre Yavuz

on the atlas — 19

• Responsible Scaling Policy v3 — LessWrong7 savers
• Anthropic Drops Flagship Safety Pledge | TIME4 savers
• Plans A, B, C, and D for misalignment risk4 savers
• İdeolojik Çölün Serabı: Doğan Avcıoğlu Neden ve Nasıl Dirildi? | Haydar Barış Aybakır | Fikirtepe Medya1 savers
• Kadrocular - Vikipedi1 savers
• Policy Options for Preserving Chain of Thought Monitorability — Institute for AI Policy and Strategy1 savers
• A small number of samples can poison LLMs of any size \ Anthropic6 savers
• Operations in AI Safety: A One-Year Perspective and Advice — EA Forum1 savers
• Youth Movements - by Robin Hanson - Overcoming Bias1 savers
• The Risk of Gradual Disempowerment from AI1 savers
• A Simple Explanation of AGI Risk — AI Alignment Forum2 savers
• Safety as a Scientific Pursuit - by Tom McGrath1 savers
• The Gentle Romance — LessWrong1 savers
• The Best Tacit Knowledge Videos on Every Subject — LessWrong15 savers
• Learning By Writing42 savers
• Congress has started taking AGI more seriously1 savers
• Research Debt28 savers
• Nailing the basics – Theories of change — EA Forum2 savers
• What an actually pessimistic containment strategy looks like — LessWrong1 savers

highlights — 1

• Achieving a research-level understanding of most topics is like climbing a mountain. Aspiring researchers must struggle to understand vast bodies of work that came before them, to learn techniques, and to gain intuition. Upon reaching the top, the new researcher begins doing novel work, throwing new stones onto the top of the mountain and making it a little taller for whoever comes next

  Research Debt