Go to lesswrong.com and do some searches about "goal," "reward," "agent," "alignment" etc. This has been addressed extensively. I don't like Yudkowsky's extreme framing about killing everyone instantly, nanotech, or very high probabilities of doom, so I'd avoid his stuff and read what others said.

One example: suppose you can use the open-source LLAMA 6, released in 2027, to create a bot that earns billions by trading obscure currencies. It's not even deceptive - it straightforwardly tells you that scaling up your account will eventually cause economic instabilities in a small African country with some probability (Soros's trading forced the British government to withdraw from the European Exchange Rate Mechanism (ERM) and devalue its currency in 1992). Do you think nobody will do it? Would every single person care or even foresee that it could lead to widespread suffering (such as the inflation in Venezuela or Argentina)?