full transcript
"From the Ted Talk by Stuart Russell: 3 principles for creating safer AI"

Unscramble the Blue Letters

And then when the machine is swhiectd off, that third principle comes into play. It learns something about the oeitcjbevs it should be pursuing, because it learns that what it did wasn't right. In fact, we can, with stlibaue use of Greek symbols, as mathematicians usually do, we can actually prove a theorem that says that such a robot is provably bneeaificl to the human. You are provably better off with a machine that's designed in this way than without it. So this is a very simple example, but this is the first step in what we're trying to do with human-compatible AI.

Open Cloze

And then when the machine is ________ off, that third principle comes into play. It learns something about the __________ it should be pursuing, because it learns that what it did wasn't right. In fact, we can, with ________ use of Greek symbols, as mathematicians usually do, we can actually prove a theorem that says that such a robot is provably __________ to the human. You are provably better off with a machine that's designed in this way than without it. So this is a very simple example, but this is the first step in what we're trying to do with human-compatible AI.

Solution

  1. switched
  2. beneficial
  3. suitable
  4. objectives

Original Text

And then when the machine is switched off, that third principle comes into play. It learns something about the objectives it should be pursuing, because it learns that what it did wasn't right. In fact, we can, with suitable use of Greek symbols, as mathematicians usually do, we can actually prove a theorem that says that such a robot is provably beneficial to the human. You are provably better off with a machine that's designed in this way than without it. So this is a very simple example, but this is the first step in what we're trying to do with human-compatible AI.

ngrams of length 2

collocation frequency
human race 5
good idea 3
lee sedol 3
real world 3
king midas 3
behave badly 3

Important Words

  1. ai
  2. beneficial
  3. designed
  4. fact
  5. greek
  6. human
  7. learns
  8. machine
  9. mathematicians
  10. objectives
  11. play
  12. principle
  13. provably
  14. prove
  15. pursuing
  16. robot
  17. simple
  18. step
  19. suitable
  20. switched
  21. symbols
  22. theorem