Home Creators Posts Import Register Favorites Logout
haven't archived this post yet. have a subscription? use the importer!

Content

An experimental video. Like a let's-play, this is a "let's read".

We're reading through Rohin Shah's Alignment Newsletter and talking about it. Let me know what you think!

Would you want me to read everything even if the video ends up really long? Or just do the bits where I have something to say?

https://mailchi.mp/1e757d9b05cb/alignment-newsletter-52?e=a708728e18

More information about the Newsletter here: http://rohinshah.com/alignment-newsletter/

https://youtu.be/19scvuLpaBA

Files

Previews only

Let's Read the Alignment Newsletter #52

An experimental video. Like a let's-play, this is a "let's read". We're reading through Rohin Shah's Alignment Newsletter and talking about it. Let me know what you think! https://mailchi.mp/1e757d9b05cb/alignment-newsletter-52?e=a708728e18 More information about the Newsletter here: http://rohinshah.com/alignment-newsletter/

Comments

Wodenborn

I like this very much. You do a good job of unpacking sentences and concepts that might be obvious to an expert, but actually have a lot going on.

Anonymous

This is good and I like the deeper level of discussion. Specifically with regard to the idea of testing superhuman AI by making them debate, I believe this is how I relate to professions that I am not a member of. I know they have conferences and debates and that I can read their proceedings. There is the possibility they will conspire. Axelrod showed this when some genetic algorithms conspired.