What is AI alignment? | BlueDot Impact
This article explains key concepts that come up in the context of AI alignment. These terms are only attempts at gesturing at the underlying ideas, and the ideas are what is important. There is no strict consensus on which name should correspond to which idea, and different people use the terms differently.[1] This article explains how we use these words on our AI Alignment course, and how alignment research contributes to AI safety. AI is likely to have an unprecedented impact on the world — possibly comparable to the industrial revolution or even larger. Terms to describe these systems include: Artificial General Intelligence, or AGI: A notoriously contentious term which offers an endless space for arguments. To avoid such arguments, we can talk about certain properties, such as: * performance on specific tasks; and * generality (i.e. what range of tasks can the AI perform). For example, some authors define human-level AI as an AI which can perform at least 95% of economically-releva
Blog What is AI alignment? Adam Jones Mar 01, 2024 54 6 3 Share This article explains key concepts that come up in the context of AI alignment. These terms are only attempts at gesturing at the underlying ideas, and the ideas are what is important. There is no strict consensus on which name should correspond to which idea, and different people use the terms differently. 1 This article explains how we use these words on our AI Alignment course , and how alignment research contributes to AI safety. Making AI go well AI is likely to have an unprecedented impact on the world — possibly comparable
Explore this link on the map →related reading
- What is AI alignment? - by Adam Jones - BlueDot Impactblog.bluedot.org
- What is AI alignment? - by Adam Jones - BlueDot Impactaisafetyfundamentals.com
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- AGI Ruin: A List of Lethalities — LessWronglesswrong.com
- Current AIs seem pretty misaligned to me — LessWronglesswrong.com
- Outer vs inner misalignment: three framings — AI Alignment Forumalignmentforum.org
- Outer vs inner misalignment: three framings — LessWronglesswrong.com
- Shah and Yudkowsky on alignment failures — LessWronglesswrong.com
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- Another (outer) alignment failure story — AI Alignment Forumalignmentforum.org
- [2605.10310] Positive Alignment: Artificial Intelligence for Human Flourishingarxiv.org
- Current AIs seem pretty misaligned to meblog.redwoodresearch.org