Complexity of Value - LessWrong
Complexity of value is the thesis that human values have high Kolmogorov complexity; that our preferences, the things we care about, cannot be summed by a few simple rules, or compressed. Fragility of value is the thesis that losing even a small part of the rules that make up our values could lead to results that most of us would now consider as unacceptable (just like dialing nine out of ten phone digits correctly does not connect you to a person 90% similar to your friend). For example, all of our values except novelty might yield a future full of individuals replaying only one optimal experience through all eternity. Related: Ethics & Metaethics, Fun Theory, Preference, Wireheading Many human choices can be compressed, by representing them by simple rules - the desire to survive produces innumerable actions and subgoals as we fulfill that desire. But people don't just want to survive - although you can compress many human activities to that desire, you cannot compress all of human e
x Complexity of value — LessWrong Main 3 LW Wiki Complexity of value Edited by Eliezer Yudkowsky , et al. last updated 14th Apr 2016 Introduction "Complexity of value" is the idea that if you tried to write an AI that would do right things (or maximally right things, or adequately right things) without further looking at humans (so it can't take in a flood of additional data from human advice, the AI has to be complete as it stands once you're finished creating it), the AI's preferences or utility function would need to contain a large amount of data ( algorithmic complexity ). Conversely, if
Explore this link on the map →related reading
- Shtetl-Optimized >> Blog Archive >> The First Law of Complexodynamicsscottaaronson.blog
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- Value systematization: how values become coherent (and misaligned) — LessWronglesswrong.com
- Value systematization: how values become coherent (and misaligned) — AI Alignment Forumalignmentforum.org
- Value is Fragile — LessWronglesswrong.com
- Value Learning Needs a Low-Dimensional Bottleneck — LessWronglesswrong.com
- What Does It Mean to Align AI With Human Values? | Quanta Magazinequantamagazine.org
- Say Not "Complexity" — LessWronglesswrong.com
- A Technical Introduction to Solomonoff Induction without K-Complexity — LessWronglesswrong.com
- What’s Your P(WEIRD)? — LessWronglesswrong.com
- What Is The Alignment Problem? — LessWronglesswrong.com
- Complexity no Bar to AI · Gwern.netgwern.net