The case against AI alignment - LessWrong
Trigger warning: Discussion of seriously horrific shit. Honestly, everything is on the table here so if you're on the lookout for trigger warnings you should probably stay away from this conversation…
x The case against AI alignment — LessWrong Risks of Astronomical Suffering (S-risks) AI World Modeling World Optimization Frontpage 127 The case against AI alignment by andrew sauer 24th Dec 2022 6 min read 110 127 Trigger warning: Discussion of seriously horrific shit. Honestly, everything is on the table here so if you're on the lookout for trigger warnings you should probably stay away from this conversation. Any community of people which gains notability will attract criticism. Those who advocate for the importance of AI alignment are no exception. It is undoubtable that you have all hear
saved by
related reading
- The Artificiality of Alignmentjoinreboot.org
- AGI Ruin: A List of Lethalities — LessWronglesswrong.com
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- What failure looks like — LessWronglesswrong.com
- What failure looks like — AI Alignment Forumalignmentforum.org
- The Problem — LessWronglesswrong.com
- Alignment & Succession: The Two Bars of Alignmentnosetgauge.com
- Explore: AI alignmentarbital.greaterwrong.com
- Value Alignment Is a Pseudo Conceptzilanqian.substack.com
- Existential Risk from AI: An Exposition for Mathematiciansalkjash.github.io
- Another (outer) alignment failure story — AI Alignment Forumalignmentforum.org
- What’s Your P(WEIRD)? — LessWronglesswrong.com