Janus' Simulators
astralcodexten.substack.com · 2,108 words · saved by 2 readers
This post isn't exactly about AI, but bear with me
This post isn’t exactly about AI. But the first three parts will be kind of technical AI stuff, so bear with me. Janus writes about Simulators. In the early 2000s, the early AI alignment pioneers - Eliezer Yudkowsky, Nick Bostrom, etc - deliberately started the field in the absence of AIs worth aligning. After powerful AIs existed and needed aligning, it might be too late. But they could glean some basic principles through armchair speculation and give their successors a vital head start. Without knowing how future AIs would work, they speculated on three potential motivational systems:…
saved by
related reading
- Simulators — LessWronglesswrong.com
- Cyborgism — LessWronglesswrong.com
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- The Artificiality of Alignmentjoinreboot.org
- trees are harlequins, words are harlequins - the voidnostalgebraist.tumblr.com
- Why Simulator AIs want to be Active Inference AIs — AI Alignment Forumalignmentforum.org
- GPTs are Predictors, not Imitators — AI Alignment Forumalignmentforum.org
- Simulated Users & Sad LLMs1a3orn.com
- Cyborgism — AI Alignment Forumalignmentforum.org
- Artificial General Intelligence Is Already Herenoemamag.com
- God Help Us, Let's Try To Understand The Paper On AI Monosemanticityastralcodexten.com
- Thoughts on AI in academiatheinfinitesimal.substack.com