Search results

From RB Wiki
  • ...probable future states of the world. But to avoid [[Goodhart's law]] and [[wireheading]], it would likely be dangerous to do so directly. Instead, Bob could enabl
    5 KB (799 words) - 09:58, 4 March 2020
  • ...vacy]], [[human liabilities]], [[interpretability]], [[reward hacking]], [[wireheading]] and [[instrumental convergence]]. Because of all such problems, it seems
    8 KB (1,107 words) - 10:37, 2 March 2020