safety
Concerns with safety have to do with technologies causing harm to people, often – though not always – as a result of malfunction. This is why safety is related to concerns about reliability.
- Note that this is quite different from the issue of personal safety that is central to privacy concerns regarding stalkers.
What Is AI Safety? from Scott Aaronson's lecture on AI Safety
So, the rapidly-growing field of AI safety. People use different terms, so I want to clarify this a little bit. To an outsider hearing the terms “AI safety,” “AI ethics,” “AI alignment,” they all sound like kind of synonyms, right? It turns out, and this was one of the things I had to learn going into this, that AI ethics and AI alignment are two communities that despise each other. It’s like the People’s Front of Judea versus the Judean People’s Front from Monty Python.
To oversimplify radically, “AI ethics” means that you’re mainly worried about current AIs being racist or things like that—that they’ll recapitulate the biases that are in their training data. This clearly can happen: if you feed GPT a bunch of racist invective, GPT might want to say, in effect, “sure, I’ve seen plenty of text like that on the Internet! I know exactly how that should continue!” And in some sense, it’s doing exactly what it was designed to do, but not what we want it to do. More generally, AI ethics people are worried that machine learning systems will be misused by greedy capitalist enterprises to become even more obscenely rich and things like that.
At the other end of the spectrum, “AI alignment” is where you believe that really the main issue is that AI will become superintelligent and kill everyone, just destroy the world. The usual story here is that someone puts an AI in charge of a paperclip factory, they tell it to figure out how to make as many paperclips as possible, and the AI (being superhumanly intelligent) realizes that it can invent some molecular nanotechnology that will convert the whole solar system into paperclips.
You might say, well then, you just have to tell it not to do that! Okay, but how many other things do you have to remember to tell it not to do? And the alignment people point out that, in a world filled with powerful AIs, it would take just a single person forgetting to tell their AI to avoid some insanely dangerous thing, and then the whole world could be destroyed.