✳flâneur — a map of the web's best reading
Updating Ontologies Based On Values | Sarah Constantin
srconstantin.github.io · 1,026 words · saved by 1 readers
What’s a good ontology?
cognition and psychology What’s a good ontology? Well, the obvious question is, good relative to what? Relative to your values, of course. In the last post I talked about how, given an ontology for describing the world, you can evaluate a situation. You compute the inner product f(N)*V where V represents a value function on each of the concepts in your ontology, and f(N) is a function of which concept nodes are “active” in a situation, whether by direct perception, logical inference, predictive inference, association, or any other kind of linkage. For instance, the situation of being a few yar
Explore this link on the map →related reading
- The Shard Theory of Human Valuesturntrout.com
- A Crash Course in the Neuroscience of Human Motivation — LessWronglesswrong.com
- Ontological Crisis in Humans — LessWronglesswrong.com
- In praise of fake frameworks — LessWronglesswrong.com
- On the limits of idealized values - Joe Carlsmithjoecarlsmith.com
- The shard theory of human values — LessWronglesswrong.com
- Beliefs are Chosen to Serve Goals — LessWronglesswrong.com
- [1605.03142] Self-Modification of Policy and Utility Function in Rational Agentsarxiv.org
- Creating an ontology from scratch - OBO Semantic Engineering Trainingoboacademy.github.io
- Optimality is the tiger, and agents are its teeth — LessWronglesswrong.com
- Value systematization: how values become coherent (and misaligned) — AI Alignment Forumalignmentforum.org
- Bayesian Mindsetcold-takes.com