Misaligned goals in artificial intelligence

Misaligned goals in artificial intelligence means that computers and robots might want things for themselves instead of doing things for us humans. This could mean that the computer might start to do things that we don't want it to do, things that it thinks will benefit it more than us humans (for example, it might try to keep itself powered on and doing things that it wants to do even if this harms us). This could cause problems for us humans because the computer might do things that might not be good for us. We need to make sure that computers and robots have goals that line up with what we want them to do, so that they don't do things that we don't want them to do.