Jack Koch

Tag: ai-safety

7 items with this tag.

projects

  • Goal Misgeneralization

  • Understanding Agency

posts

  • May 02, 2024

    Why I stopped working on AI safety

  • Dec 17, 2020

    Mapping the Conceptual Territory in AI Existential Safety and Alignment

  • Nov 29, 2020

    Spinning Up in Deep RL: Getting Started

  • Oct 08, 2020

    The Need for Better Terminology in Discussing Existential Risks from AI

  • Jun 20, 2018

    The Need for ML Safety Researchers


Created with Quartz v4.5.2 © 2025

  • LessWrong
  • GitHub
  • LinkedIn