Intro to AI Safety, Remastered

Channel:Robert Miles AI Safety · Length:18:04 · Published:2021-06-24 · Views:211272

Watch on YouTube

Summary

Robert Miles gives a remastered introduction to AI safety, adapted from a talk in London. It lays out why advanced AI could go wrong and answers common objections.

Why HN recommends it

The default link for newcomers wanting an approachable, entertaining introduction to AI risk and alignment.

It's quite an approachable intro, often entertaining — HN, 2023

AI safety, AGI & impact

Subtitles (excerpt)

Hi. This video is a recording of a talk that I gave a while back. I already published a version of it on my second channel, but did you even know I had a second channel? Most people don't. I thought more people should see it, so I remastered it. I cleaned it up, improved the graphics, and yeah, this is that. Enjoy. Right. Hello, everyone. My name is Robert Miles. I am usually doing this on YouTube. I'm not really used to public speaking. I'm not used to not being able to edit out my mistakes. There may be mistakes. Also, I may go too quickly. Sorry, not sorry. So when it comes to AI safety, you can kind of divide it up into four areas along two axes. You've got your short-term and your long-term, and you've got accident risks and misuse risks, and that's kind of a useful way to divide things up. AI safety covers everything. The area that interests me most is the long-term accident risks. I think once you have very powerful AI systems, it almost doesn't matter if they're being used by the right people or the wrong people or what you're trying to do with them. The difficulty is in keeping them under control at all. So that's what I'm going to be talking about. What is AI safety? Why is it important?

On Hacker News

I strongly suggest anyone doubtful of the reasoning behind these concerns or asking questions like "well why don't we just do x to solve this?" go check out Robert Miles' YouTube channel[1]. It's quite an approachable intro, often entertaining, doesn't take a long time to get through all the core videos, and very thoroughly answers all the "why not just do x" questions if you go through the whole… — durbleflorp, 2023-01
If only. There's a lot of space in between "our morality" (please do define that) and "what we want to be" where AGI can royally screw us. Check out Robert Miles on AI safety, here's a good intro: [VIDEO] — albumen, 2023-10
The basic argument is trivial: it is plausible that future systems achieve superhuman capability; capable systems necessarily have instrumental goals; instrumental goals tend to converge; human preferences are unlikely to be preserved when other goals are heavily selected for unless intentionally preserved; we don't know how to make AI systems encode any complex preference robustly. Robert Miles'… — Veedrac, 2023-05
I recommend Robert Miles's YouTube channel, and his "Intro to AI Safety, Remastered" is a good place to start: [VIDEO] I find Robert Miles worryingly plausible when he says (about 12:40 into the video) "if you have a sufficiently powerful agent and you manage to come up with a really good objective function, which covers the top 20 things that humans value, the 21st thing that humans value is pro… — lambertsimnel, 2023-05
Is there any chance you could add some links to AI Safety Resources such as Joe Carlsmith's Power Seeking AI ( [LINK] ) or Rob Miles Introduction to AI Safety ( [VIDEO] )? Perhaps you could link to a resource on the AI box experiment as well? I know you vaguely gesture at it, but would likely be better to explicitly link people to resources if they haven't heard of it themselves. — casebash, 2022-12

Related videos