My favorite for AI researchers is Ajeya's Without specific countermeasures, because I think it does a really good job being concrete about a training set up leading to deceptive alignment. It also is sufficiently non-technical that a motivated person not familiar with AI could understand the key points.

[-]JakubK3y20

Forgot to include this. It's sort of a more opinionated and ML-focused version of Carlsmith's report and has a corresponding video/talk (as does Carlsmith).

Michael Tontchev

Jun 07, 2023

Want to add this one:

https://www.lesswrong.com/posts/B8Djo44WtZK6kK4K5/outreach-success-intro-to-ai-risk-that-has-been-successful

This is the note I wrote internally at Meta - it's had over 300 reactions, as well as people reaching out to me saying it has convinced them to switch to working on alignment.

[-]JakubK2y20

Thanks for writing and sharing this. I've added it to the doc.

Tor Økland Barstad

Dec 13, 2022

Good initiative.

Regarding introductions to a popular audience, I feel like Tim Urban wrote an intro that also is worth mentioning: Part 1 - Part 2 - Reply from Luke Muehlhauser

Another one is A Response to Steven Pinker on AI (Rob Miles)

Btw, I sometimes recommend Superintelligence by Nick Bostrom (but that's an entire book)

Will be interesting to see what kinds of introductions that are available one or a few years from now. Some people have created good introductions, but I do feel as if there is room for improvement.

Btw, I think Rob Miles is working on a collaborative FAQ: https://stampy.ai/wiki/Main_Page (which he talks about here)