Maximilian Kaufmann

• Maximilian Kaufmann 7 Oct 2022 23:38 UTC

  LW: 15 AF: 8

  0

  AF

  on: More ex­am­ples of goal misgeneralization

  How hard was it to find the examples of goal misgeneralization? Did the results take much “coaxing”?

• Maximilian Kaufmann 16 May 2023 22:15 UTC

  3 points

  2

  on: Pro­posal: we should start refer­ring to the risk from un­al­igned AI as a type of *ac­ci­dent risk*

  A point against that particular terminology which you might find interesting. https://​​www.lesswrong.com/​​posts/​​6bpW2kyeKaBtuJuEk/​​why-i-hate-the-accident-vs-misuse-ai-x-risk-dichotomy-quick