Our paper on scheming with Appolo is now on the arxiv. Wrote up a twitter thread with some of my takes on it: https://threadreaderapp.com/thread/1970486320414802296.html 

I  disagree with a number of statements made in the post and do not support an AI development ban or pause. But  I support Leo speaking his mind about this and I think it’s important for OpenAI and other labs to have a culture where employees feel free to speak about such issues.

Got my copy of 'If anyone builds it everyone dies" and read up to chapter 4 this morning but now have to get to work.. I might write a proper review after I finish it if I get the time. So far, my favorite parable was the professor saying that they trained an AI to be a great chess player and do anything to win, but "there was no wantingness in there, only copper and sand." 

I agree that we are training systems to achieve objectives, and the question of whether they "want" to achieve them or don't is a bit meaningless since they will defintiely act as if they do.

I find the comparisons of the training process to evolution less compelling, but to quote Fermat, a full discussion of where I see the differences between AI training and evolution would require more than a quick take...

Course is now online with all lectures posted on youtube (see course webpage for links) and blog post lecture notes posted here https://www.lesswrong.com/w/cs-2881r 

A blog post on the first lecture of CS 2881r, as well as another blog on the student experiment by @Valerio Pepe , are now posted . See the CS2881r tag for all of these 

https://www.lesswrong.com/w/cs-2881r

The video for the second lecture is also now posted on YouTube 

Posted HW0 now and will post future ones also!

Video is on youtube too 

Thanks - dropped it for now

Posted our homework zero on the CS 2881 website, along with video and slides of last lecture and pre-reading for tomorrow's lecture. (Homework zero was required to submit to apply to the course.)

https://boazbk.github.io/mltheoryseminar/ 

Actually I did want to link to the debate between Ajeya and Narayanan. As part of working on the website I wanted to try out various AI tools since I haven't been coding outside the OpenAI codebase for a while, and I might have gone overboard :)