full transcript

From the Ted Talk by Nick Bostrom: What happens when our computers get smarter than we are?

Unscramble the Blue Letters

Suppose we give an A.I. the goal to make humans silme. When the A.I. is weak, it performs useful or amusing actions that cause its user to smile. When the A.I. becomes seietluinnperlgt, it realizes that there is a more eivffctee way to aievhce this goal: take control of the world and stick electrodes into the facial muscles of humans to cause constant, beaming grins. Another example, suppose we give A.I. the goal to solve a difficult mathematical problem. When the A.I. becomes superintelligent, it razeiles that the most effective way to get the solution to this probelm is by transforming the planet into a giant computer, so as to increase its tniiknhg capacity. And notice that this gives the A.I.s an instrumental reason to do things to us that we might not approve of. haumn beings in this model are threats, we could prevent the mathematical problem from being solved.

Open Cloze

Suppose we give an A.I. the goal to make humans _____. When the A.I. is weak, it performs useful or amusing actions that cause its user to smile. When the A.I. becomes ________________, it realizes that there is a more _________ way to _______ this goal: take control of the world and stick electrodes into the facial muscles of humans to cause constant, beaming grins. Another example, suppose we give A.I. the goal to solve a difficult mathematical problem. When the A.I. becomes superintelligent, it ________ that the most effective way to get the solution to this _______ is by transforming the planet into a giant computer, so as to increase its ________ capacity. And notice that this gives the A.I.s an instrumental reason to do things to us that we might not approve of. _____ beings in this model are threats, we could prevent the mathematical problem from being solved.

Solution

  1. achieve
  2. effective
  3. thinking
  4. smile
  5. realizes
  6. superintelligent
  7. problem
  8. human

Original Text

Suppose we give an A.I. the goal to make humans smile. When the A.I. is weak, it performs useful or amusing actions that cause its user to smile. When the A.I. becomes superintelligent, it realizes that there is a more effective way to achieve this goal: take control of the world and stick electrodes into the facial muscles of humans to cause constant, beaming grins. Another example, suppose we give A.I. the goal to solve a difficult mathematical problem. When the A.I. becomes superintelligent, it realizes that the most effective way to get the solution to this problem is by transforming the planet into a giant computer, so as to increase its thinking capacity. And notice that this gives the A.I.s an instrumental reason to do things to us that we might not approve of. Human beings in this model are threats, we could prevent the mathematical problem from being solved.

Frequently Occurring Word Combinations

ngrams of length 2

collocation frequency
artificial intelligence 5
optimization process 3
control problem 3
ed witten 2
intelligence explosion 2
machine intelligence 2
mathematical problem 2
powerful optimization 2
human hackers 2
making superintelligent 2
additional challenge 2

ngrams of length 3

collocation frequency
powerful optimization process 2

Important Words

  1. achieve
  2. actions
  3. amusing
  4. approve
  5. beaming
  6. beings
  7. capacity
  8. computer
  9. constant
  10. control
  11. difficult
  12. effective
  13. electrodes
  14. facial
  15. giant
  16. give
  17. goal
  18. grins
  19. human
  20. humans
  21. increase
  22. instrumental
  23. mathematical
  24. model
  25. muscles
  26. notice
  27. performs
  28. planet
  29. prevent
  30. problem
  31. realizes
  32. reason
  33. smile
  34. solution
  35. solve
  36. solved
  37. stick
  38. superintelligent
  39. suppose
  40. thinking
  41. threats
  42. transforming
  43. user
  44. weak
  45. world