The space of systems and the space of maps — LessWrong
When we're trying to do AI alignment, we're often studying systems which don't yet exist. This is a pretty weird epistemic activity, and seems really…
x The space of systems and the space of maps — LessWrong Epistemology Research Agendas Rationality Frontpage 38 The space of systems and the space of maps by Jan_Kulveit , rosehadshar , Nora_Ammann , clem_acs 22nd Mar 2023 AI Alignment Forum 6 min read 0 38 Ω 21 When we're trying to do AI alignment, we're often studying systems which don't yet exist. This is a pretty weird epistemic activity, and seems really hard to get right. This post offers one frame for thinking about what we're actually doing when we're thinking about AI alignment: using parts of the space of maps to reason about parts o
Explore this link on the map →related reading
- LessWronglesswrong.com
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- AGI Ruin: A List of Lethalities — LessWronglesswrong.com
- Where I agree and disagree with Eliezer — LessWronglesswrong.com
- 2023 letter | Zhengdongzhengdongwang.com
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- Shah and Yudkowsky on alignment failures — LessWronglesswrong.com
- A minimal viable product for alignment - by Jan Leikealigned.substack.com
- The Plan - 2025 Update — LessWronglesswrong.com
- Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com
- What is AI alignment? - by Adam Jones - BlueDot Impactblog.bluedot.org
- A positive case for how we might succeed at prosaic AI alignment — AI Alignment Forumalignmentforum.org