Different senses in which two AIs can be “the same” — LessWrong
Sometimes people talk about two AIs being “the same” or “different” AIs. We think the intuitive binary of “same vs. different” conflates several conc…
x Different senses in which two AIs can be “the same” — LessWrong AI World Modeling Frontpage 83 Different senses in which two AIs can be “the same” by Vivek Hebbar , Buck 24th Jun 2024 AI Alignment Forum 5 min read 3 83 Ω 40 Sometimes people talk about two AIs being “the same” or “different” AIs. We think the intuitive binary of “same vs. different” conflates several concepts which are often better to disambiguate. In this post, we spell out some of these distinctions. We don’t think anything here is particularly novel; we wrote this post because we think it’s probably mildly helpful for peop
saved by
related reading
- Role-playing vs Self-modelling — LessWronglesswrong.com
- Simulators — LessWronglesswrong.com
- The Artificial Selftheartificialself.ai
- The Artificial Self — LessWronglesswrong.com
- The behavioral selection model for predicting AI motivations — LessWronglesswrong.com
- Self-Other Overlap: A Neglected Approach to AI Alignment — LessWronglesswrong.com
- Current AIs seem pretty misaligned to me — LessWronglesswrong.com
- Deep Deceptiveness — LessWronglesswrong.com
- From personas to intentions: towards a science of motivations for AI models — LessWronglesswrong.com
- The Case Against AI Control Research — LessWronglesswrong.com
- Models Don't "Get Reward" — LessWronglesswrong.com
- Defining alignment research — LessWronglesswrong.com