Russell argues that as robots take on more complicated tasks咧欣，it’s necessary to translate our morals into AI language藏鹊。

For example，if a robot does chores around the house膘盖，you wouldn’t want it to put the pet cat in the oven to make dinner for the hungry children胧弛。 “You would want that robot preloaded with a good set of values尤误，”said Russell。

Some robots are already programmed with basic human values结缚。For example损晤，mobile robots have been programmed to keep a comfortable distance from humans。Obviously there are cultural differences红竭，but if you were talking to another person and they came up close in your personal space尤勋，you wouldn’t think that’s the kind of thing a properly brought-up person would do。

It will be possible to create more sophisticated moral machines茵宪，if only we can find a way to set out human values as clear rules最冰。

Robots could also learn values from drawing patterns from large sets of data on human behavior。They are dangerous only if programmers are careless稀火。

The biggest concern with robots going against human values is that human beings fail to so sufficient testing and they’ve produced a system that will break some kind of taboo（禁忌）暖哨。

One simple check would be to program a robot to check the correct course of action with a human when presented with an unusual situation。

If the robot is unsure whether an animal is suitable for the microwave凰狞，it has the opportunity to stop篇裁，send out beeps（嘟嘟聲），and ask for directions from a human赡若。If we humans aren’t quite sure about a decision达布，we go and ask somebody else。

The most difficult step in programming values will be deciding exactly what we believe in moral逾冬，and how to create a set of ethical rules黍聂。But if we come up with an answer，robots could be good for humanity粉渠。

46.What does the author say about the threat of robots分冈？

A）It may constitute a challenge to computer progranmers。

B）It accompanies all machinery involving high technology霸株。

C）It can be avoided if human values are translated into their language雕沉。

D）It has become an inevitable peril as technology gets more sophisticated。

47.What would we think of a person who invades our personal space according to the author去件？

A）They are aggressive坡椒。

B）They are outgoing。

C）They are ignorant尤溜。

D）They are ill-bred倔叼。

48.How do robots learn human values？

A）By interacting with humans in everyday life situations宫莱。

B）By following the daily routines of civilized human beings丈攒。

C）By picking up patterns from massive data on human behavior。

D）By imitating the behavior of property brought-up human beings。

49.What will a well-programmed robot do when facing an unusual situation巡验？

A）keep a distance from possible dangers际插。

B）Stop to seek advice from a human being。

C）Trigger its built-in alarm system at once显设。

D）Do sufficient testing before taking action框弛。

50.What is most difficult to do when we turn human values into a programmable code？

A）Determine what is moral and ethical捕捂。

B）Design some large-scale experiments瑟枫。

C）Set rules for man-machine interaction。

D）Develop a more sophisticated program指攒。

答案:CDCDA