What failure looks like - LessWrong
Paul Christiano paints a vivid and disturbing picture of how AI could go wrong, not with sudden violent takeover, but through a gradual loss of human…
x What failure looks like — LessWrong Best of LessWrong 2019 AI Risk Threat Models (AI) AI Takeoff More Dakka AI World Modeling World Optimization Curated 466 What failure looks like by paulfchristiano 17th Mar 2019 AI Alignment Forum 10 min read 56 466 Ω 111 The stereotyped image of AI catastrophe is a powerful, malicious AI system that takes its creators by surprise and quickly achieves a decisive advantage over the rest of humanity. I think this is probably not what failure will look like, and I want to try to paint a more realistic picture. I’ll tell the story in two parts: Part I : machin
saved by
- Hangyul Lyna Kim
- Sarah Pan
- Callistus
- Lydia Nottingham
- Timothy Kostolansky
- Raphael Mu
- Will Anderson
- Carolanne Jiang
- Mari M
- Dillon Nguyen
- Eliana Du
- Goutham N
related reading
- What failure looks like — AI Alignment Forumalignmentforum.org
- Another (outer) alignment failure story — AI Alignment Forumalignmentforum.org
- What Failure Looks Like: Distilling the Discussion — LessWronglesswrong.com
- AI Could Defeat All Of Us Combined — LessWronglesswrong.com
- Gradual Disempowermentgradual-disempowerment.ai
- Dario Amodei — The Adolescence of Technologydarioamodei.com
- The Case Against AI Control Research — LessWronglesswrong.com
- The Problem — LessWronglesswrong.com
- Dario Amodei — The Adolescence of Technologydarioamodei.com
- My AI Opinions - by Scott Alexander - Astral Codex Tensubstack.com
- Fields that I reference when thinking about AI takeover prevention — LessWronglesswrong.com
- Current AIs seem pretty misaligned to meblog.redwoodresearch.org