Aligning AI With Shared Human Values.
Dan HendrycksCollin BurnsSteven BasartAndrew CritchJerry LiDawn SongJacob SteinhardtPublished in: ICLR (2021)
Keyphrases
- artificial intelligence
- human level
- ai systems
- neural network
- human intelligence
- standard deviation
- human experts
- user defined
- intelligent systems
- image registration
- case based reasoning
- human beings
- ai community
- real time
- color images
- machine intelligence
- web intelligence
- human interaction
- human behavior
- parameter values
- probability distribution
- cognitive psychology
- social networks
- artificial general intelligence
- computational models
- knowledge representation
- artificially intelligent