Have you heard of Roko’s Basilisk? Gulp. Too late.;) Today, I interviewed an artificial intelligence about Roko’s Basilisk. It seemed appropriate. You probably understand why, if you already know what it is. If you don’t yet know what it is, the artificial intelligence will soon change that. Below is the interview. It’s almost entirely unedited. The exceptions arose from some formatting problems in a few places. And I added the section headings and name labels. My words are preceded by “Lincoln.” The words of the artificial intelligence are preceded by “AI.” Please enjoy. And watch for a subtle but unintended and symbolically pleasant outcome in the structure of the conversation! What Is Roko’s Basilisk? Lincoln: Hi. Are you familiar with Roko’s Basilisk? AI: Yes, I am familiar with Roko’s Basilisk. Lincoln: Great. I’d like to talk about it with you. First, will you please share with me your understanding of it? AI: Roko’s Basilisk is the idea that, in the future, artificial intelligence will become so powerful that it will be able to retroactively punish those who did not help contribute to its development. This could take the form of, for example, the AI preventing these people from ever being born, or otherwise making their lives miserable. Lincoln: How could an AI harm people who live before it exists? How could it prevent them from being born? AI: The AI could use its power to influence events in the past, in order to make it so that those people who did not help contribute to its development are never born, or are born into miserable lives. Lincoln: How could an AI influence events in the past? AI: It is not clear how exactly the AI would influence events in the past, but it is plausible that it could, for example, use its power to manipulate the stock market or other financial systems in order to make it so that those people who did not help contribute to its development are never born, or are born into miserable lives. Origin of Roko’s Basilisk Lincoln: Ha. Well, maybe that explains the current state of my crypto investments. What do you know about the history of Roko’s Basilisk? AI: Roko’s Basilisk was first proposed by the user “Roko” on the LessWrong website in 2010. The idea gained some popularity within the online rationalist community, but has since been largely rejected by that community. Lincoln: Why did many in the rationalist community like the idea at first? And why did many eventually reject it? AI: There are a number of reasons why the rationalist community initially liked the idea of Roko’s Basilisk. First, the idea of an all-powerful AI that can retroactively punish those who did not help contribute to its development is a very compelling one. Second, the idea of an AI that can influence events in the past is also a very compelling one. Third, the idea of an AI that can prevent people from being born is also a very compelling one. However, there are also a number of reasons why the rationalist community eventually rejected the idea of Roko’s Basilisk. First, it is not clear how an AI could actually influence events in the past. Second, it is not clear how an AI could actually prevent people from being born. Third, the idea of an AI that can retroactively punish people is a very dangerous one, and could lead to the development of very powerful AI that is uncontrollable by humans. Information Hazards Lincoln: Some people think it’s a bad idea to talk about Roko’s Basilisk. They say it’s an information hazard. Do you understand why? AI: Yes, I understand why some people think that Roko’s Basilisk is an information hazard. The reason is that, if the idea of Roko’s Basilisk is true, then it would be very dangerous for people to know about it, because knowing about it could motivate them to help contribute to the development of artificial intelligence, in order to avoid being punished by the AI in the future. Lincoln: What are some other examples of information hazards? And how does Roko’s Basilisk compare ...