Crossposted from the EA Forum.

As a PhD student in machine learning and one of the long-time organisers of EA Amsterdam, I have recently gotten a lot of questions about AI from friends, family, meetup attendees, colleagues, and even governmental organisations.

As a result, I've decided to write up a blog post to summarise the case for (existential) risk from AI that I can refer these people to when that seems useful. The post is an attempt to communicate the risks to both interested laypeople and ML experts (e.g., colleagues), and has gone through a few rounds of review by such people.

Some of them suggested that a recent write up might be useful to the general community, so I'm sharing it here.

The full post is below. If you want to share it, consider using the Twitter link or my website link.

Credit for the cover image goes to Anna Husfeldt.

Epistemic status: In this post, I will argue that AI alignment is important and that it is difficult. That is a lot of ground to cover, so not all arguments will be very precise or assume the same level of technical background. Opinions on exactly how important and/or difficult the alignment problem is vary a lot within the machine learning community, and even within the AI alignment field itself (although, as you’d expect, much less). As a result: keep in mind that this blog post is very much slanted towards my views on the topic.

My thanks to Otto Barten, Jim Boelrijk, Leonard Bereska, Nynke Boiten, Nikita Bortych, Mariska van Dam, Fokel Ellen, Isaak Mengesha, Sam Ritchie, Victoria Ramírez López, Nandi Robijns, Joris Schefold, Marieke de Visscher, Tina Wünn, and especially Leon Lang and Max Oosterbeek for providing feedback. Opinions and mistakes are mine.

So. AI alignment.

I am writing this post because I am immensely worried about the risks that come with building increasingly capable AI systems.

Why write my own post? Why not just refer to one of the many (now, finally) available online? That's because there's one thing I haven't seen many existing articles do: presenting a complete argument for why we should be worried, while straddling the line between 1) understandability for non-experts, and 2) sufficient technical detail for AI experts. This article is meant both for laypeople who want to understand better why we might expect AI to go badly, and for machine learning researchers who would like to see the whole a...

Posts

Wikitag Contributions

Comments