#ai #llm #ai-alignment
Created at 2023-01-07
# [Anonymous feedback](https://www.admonymous.co/louis030195)
# [[Epistemic status]]
#shower-thought
Last modified date: 2023-01-07
Commit: 0
# Related
- [[Computing/Intelligence/Collective intelligence]]
- [[Computing/Intelligence/Alignment/Availability bias is strong in AI alignment research]]
- [[Computing/Intelligence/Alignment/Humanity's purpose]]
- [[Computing/Intelligence/Artificial intelligence knows us better than we know ourselves]]
# TODO
> [!TODO] TODO
# coherent extrapolated volition
Coherent extrapolated volition is a concept that considers the collective desires of humanity, and attempts to predict our future behavior. It suggests that by considering the collective desires of all humans, we can create an understanding of what the common will of humanity is. This concept can be applied to various aspects of society, from economic policy to environmental protection. By understanding the collective desires of humanity, we can create a future that is beneficial for all. Coherent extrapolated volition is a complex concept, but it has the potential to be a powerful tool in creating a better future for humanity.
## AI Alignment

By understanding the collective desires of humanity, AI systems can be better aligned with our interests, creating a more beneficial future for all.
