Explore: AI alignment - Arbital viewer
arbital.greaterwrong.com · 5,755 words · saved by 1 readers
The great civilizational problem of creating artificially intelligent computer systems such that running them is a good idea.
26 Mar 2015 23:12 UTC Executable philosophy Philosophical discourse aimed at producing a trustworthy answer or meta-answer, in limited time, which can used in constructing an Artificial Intelligence. Some computations are people It’s possible to have a conscious person being simulated inside a computer or other substrate. Researchers in value alignment theory Who’s working full-time in value alignment theory? Nick Bostrom Nick Bostrom, secretly the inventor of Friendly AI The rocket alignment problem If people talked about the problem of space travel the way they talked about AI……
saved by
related reading
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- The Artificiality of Alignmentjoinreboot.org
- What is AI alignment? - by Adam Jones - BlueDot Impactblog.bluedot.org
- What Is The Alignment Problem? — LessWronglesswrong.com
- Alignment Is Proven To Be Solvable - by SE Gygesverysane.ai
- [2605.10310] Positive Alignment: Artificial Intelligence for Human Flourishingarxiv.org
- Why AI alignment could be hard with modern deep learningcold-takes.com
- The self-unalignment problem — LessWronglesswrong.com
- The Universe from an Intentional Stancecasparoesterheld.com
- Embedded Agency (full-text version) — LessWronglesswrong.com
- Alignment & Succession: The Two Bars of Alignmentnosetgauge.com
- Can we safely automate alignment research? - Joe Carlsmithjoecarlsmith.com