Skip to content

About

AI alignment, moral agency, superintelligence, and the futures we might build.

Author

Alex Towell

Repository

Source: github.com/queelius/minds-and-machines

Key Themes

  • What happens when we build minds we can't understand?
  • Intelligence as optimization under uncertainty
  • The alignment problem: ensuring optimization serves human values
  • Fiction as a vehicle for exploring abstract risks
  • Philosophical foundations: personhood, agency, values, identity

License

MIT