https://www.universalbasicincome.ai/1-the-alignment-problem
Tristan Harris and Aza Raskin discuss how existing A.I. capabilities already pose catastrophic risks to a functional society
universal basic incomethe alignment problem
https://imbue.com/podcast/2021-05-11-podcast-episode-10-dylan-hadfield-menell/
RSS · Spotify · Apple Podcasts · Pocket Casts Dylan would love to hear any questions or comments on his paper, so feel free to reach out!…
uc berkeleyon thedylanhadfieldmenell
https://autobehave.substack.com/p/the-alignment-problem
When you have a chance, choose Alignment over Agreement - it will give you space to hone your decision making skills, allows groups to change their mind and...
the alignment problemvivekjuneja
https://deepai.org/publication/personal-universes-a-solution-to-the-multi-agent-value-alignment-problem
01/01/19 - AI Safety researchers attempting to align values of highly capable intelligent systems with those of humanity face a number of cha...
personaluniversessolutionmultiagent