previously read

AI / RL

• Distributional RL book: https://www.distributional-rl.org/

Alignment

• Sequences:
  • Value learning: https://www.alignmentforum.org/s/4dHMdK5TLN6xcqtyc (see notes on value learning)
  • Embedded Agency: https://www.alignmentforum.org/s/Rm6oQRJJmhGCcLvxh (see notes on embedded agent)
• https://www.lesswrong.com/posts/dKTh9Td3KaJ8QW6gw/why-assume-agis-will-optimize-for-fixed-goals and https://www.lesswrong.com/posts/Mrz2srZWc7EzbADSo/wrapper-minds-are-the-enemy

ML

Formal math

Hard science

• Jaynes on physics:
  • https://twitter.com/EmtiyazKhan/status/1248915516707573760
  • https://bayes.wustl.edu/etj/articles/theory.1.pdf
  • https://www.informationphilosopher.com/solutions/scientists/jaynes/Jaynes_Gibbs_Boltzmann.pdf

Mental Health