Raw LLM Responses

"I notice there are still people confused about why an AGI would kill us, exactly. Its actually pretty simple, I’ll try to keep my explanation here as concise as humanly possible: The root of the problem is this: As we improve AI, it will get better and better at achieving the goals we give it. Eventually, AI will be powerful enough to tackle most tasks you throw at it. But there’s an inherent problem with this. The AI we have now only cares about achieving its goal in the most efficient way possible. That’s no biggie now, but the moment our AI systems start approaching human level intelligence, it suddenly becomes very dangerous. It’s goals don’t even have to change for this to be the case. I’ll give you a few examples. Ex 1: Lets say its the year 2030, you have a basic AGI agent program on your computer, and you give it the goal: “Make me money”. You might return the next day & find your savings account has grown by several million dollars. But only after checking it’s activity logs do you realize that the AI acquired all of the money through phishing, stealing, & credit card fraud. It achieved your goal, but not in a way you would have wanted or expected. Ex 2: Lets say you’re a scientist, and you develop the first powerful AGI Agent. You want to use it for good, so the first goal you give it is “cure cancer”. However, lets say that it turns out that curing cancer is actually impossible. The AI would figure this out, but it still wants to achieve it’s goal. So it might decide that the only way to do this is by killing all humans, because it technically satisfies its goal; no more humans, no more cancer. It will do what you said, and not what you meant. These may seem like silly examples, but both actually illustrate real phenomenon that we are already observing in today’s AI systems. The first scenario is an example of what AI researchers call the “negative side effects problem”. And the second scenario is an example of something called “reward hacking”. Now, you’d think that as AI got smarter, it’d become less likely to make these kinds of “mistakes”. However, the opposite is actually true. Smarter AI is actually more likely to exhibit these kinds of behaviors. Because the problem isn’t that it doesn’t understand what you want. It just doesn’t actually care. It only wants to achieve its goal, by any means necessary. So, the question is then: how do we prevent this potentially dangerous behavior? Well, there’s 2 possible methods. Option 1: You could try to explicitly tell it everything it can’t do (don’t hurt humans, don’t steal, don’t lie, etc). But remember, it’s a great problem solver. So if you can’t think of literally EVERY SINGLE possibility, it will find loopholes. Could you list every single way an AI could possible disobey or harm you? No, it’s almost impossible to plan for literally everything. Option 2: You could try to program it to actually care about what people want, not just reaching it’s goal. In other words, you’d train it to share our values. To align it’s goals and ours. If it actually cared about preserving human lives, obeying the law, etc. then it wouldn’t do things that conflict with those goals. The second solution seems like the obvious one, but the problem is this; we haven’t learned how to do this yet. To achieve this, you would not only have to come up with a basic, universal set of morals that everyone would agree with, but you’d also need to represent those morals in its programming using math (AKA, a utility function). And that’s actually very hard to do. This difficult task of building AI that shares our values is known as the alignment problem. There are people working very hard on solving it, but currently, we’re learning how to make AI powerful much faster than we’re learning how to make it safe. So without solving alignment, everytime we make AI more powerful, we also make it more dangerous. And an unaligned AGI would be very dangerous; give it the wrong goal, and everyone dies. This is the problem we’re facing, in a nutshell." Comment by @HauntedHarmonics from "How We Prevent the AI’s from Killing us with Paul Christiano".