2404.10636
arxiv.org · 8,027 words · saved by 1 readers
N/A
What are human values, and how do we align AI to them? Oliver Klingefjord Ryan Lowe∗ Joe Edelman arXiv:2404.10636v2 [cs.CY] 17 Apr 2024 Meaning Alignment Institute Abstract There is an emerging consensus…
related reading
- The Artificiality of Alignmentjoinreboot.org
- [2605.10310] Positive Alignment: Artificial Intelligence for Human Flourishingarxiv.org
- Full-Stack Alignment and Thick Models of Valuefull-stack-alignment.ai
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- Alignment Is Proven To Be Solvable - by SE Gygesverysane.ai
- [2001.09768] Artificial Intelligence, Values and Alignmentarxiv.org
- [2306.13000] Apolitical Intelligence? Auditing Delphi's responses on controversial political issues in the USarxiv.org
- Value Alignment Is a Pseudo Conceptzilanqian.substack.com
- What Does It Mean to Align AI With Human Values? | Quanta Magazinequantamagazine.org
- [2607.14345] Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Valuesarxiv.org
- Aligning to Virtues — LessWronglesswrong.com
- How can LLMs help with value-guided decision making? - AI • Objectives • Instituteai.objectives.institute