Avoiding Negative Side Effects: Concrete Problems in AI Safety part 1

What Hacker News said

Strong rec jononor · 2023-01 · on “Not worried about AI that passes Turing test, but AI that fails it on purpose”

For those curious about AI safety I heavily recommend Robert Miles channel on YouTube. He has lot of good content describing out the challenges we face when trying to create safe AI. Here is one potential starting point: [this video]

Recommends nmca · 2018-05 · on “Uber Self-Driving Car That Struck Pedestrian Wasn’t Set to Stop in an Emergency”

This highlights an interesting general point - in many situations, there is no simple safe fallback policy. On a highway, an emergency stop is not safe. This is a general problem in AI safety and is covered nicely in this youtube video, as well as the paper referenced there - [this video]

Cites pas · 2018-11 · on “Superintelligence: The Idea That Eats Smart People (2016)”

Re: alignment, see the "Where are we" part of this talk: [LINK] See also the AI safety problems for concrete problems that people are currently working on - as in with code and real simulations, not "just" math and thinking: [this video] Re: scaling up. That's called intelligence explosion, there are a lot of write ups about it, but the gist of it is just that by simply increasing working memory size, thinking speed, prediction precision, pattern matching, and so on, you get to unimaginably high levels. Furthermore, if you can make a human level AI, it naturally follows that it's only a matter of time to make it slightly better. At first simply faster, simply more eloquent, a bit more emotional d