Will Capabilities Generalise More? - AI Alignment Forum
Nate andEliezer (Lethality 21) claim that capabilities generalise further than alignment once capabilities start generalising far at all. However, they have not articulated particularly detailed argu…
x Will Capabilities Generalise More? — AI Alignment Forum AI Frontpage 58 Will Capabilities Generalise More? by Ramana Kumar 29th Jun 2022 5 min read 39 58 Nate and Eliezer (Lethality 21) claim that capabilities generalise further than alignment once capabilities start generalising far at all. However, they have not articulated particularly detailed arguments for why this is the case. In this post I collect the arguments for and against the position I have been able to find or generate, and develop them (with a few hours’ effort). I invite you to join me in better understanding this claim and
Explore this link on the map →related reading
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- A central AI alignment problem: capabilities generalization, and the sharp left turn — LessWronglesswrong.com
- Alignment likely generalizes further than capabilities.beren.io
- AGI Ruin: A List of Lethalities — LessWronglesswrong.com
- Thomas Larsen's Shortform — LessWronglesswrong.com
- A positive case for how we might succeed at prosaic AI alignment — AI Alignment Forumalignmentforum.org
- Alignment remains a hard, unsolved problem — AI Alignment Forumalignmentforum.org
- Reward is not the optimization target — LessWronglesswrong.com
- Shah and Yudkowsky on alignment failures — LessWronglesswrong.com
- Why I’m optimistic about our alignment approachaligned.substack.com
- “Sharp Left Turn” discourse: An opinionated review — LessWronglesswrong.com
- Inner Alignment: Explain like I'm 12 Edition — LessWronglesswrong.com