boazbarak's Shortform

6th Sep 2025

1 min read

5

This is a special post for quick takes by boazbarak. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page.

boazbarak's Shortform

17 comments, sorted by

top scoring

Click to highlight new comments since: Today at 2:39 AM

[-]boazbarak2mo631

First lecture for CS 2881 is online https://boazbk.github.io/mltheoryseminar/ + prereading for next lecture.
Students will be posting blog posts here with lecture summaries as well.

[-]Daniel Kokotajlo2mo131

Thank you for doing this!

[-]boazbarak2mo90

Btw I assigned AI 2027 as pre reading for the first lecture! (As well as “AI as a normal technology “ and the METR paper on doubling time for tasks.)

[-]Daniel Kokotajlo2mo44

Nice. If you get a chance I'd love to hear what the students think about all of the above.

[-]peterbarnett2mo60

The Arbital link (Yudkowsky, E. – "AGI Take-off Speeds" (Arbital 2016)) in there is dead, I briefly looked at the LW wiki to try find the page but didn't see it. @Ruby?

[-]boazbarak2mo10

Thanks - dropped it for now

[-]Adam Shai2mo30

This looks great! Thanks for making the videos public.

Any chance the homework assignments/experiments can be made public?

[-]boazbarak2mo20

Posted HW0 now and will post future ones also!

[-]jsd2mo10

Neat!

"Does AI Progress Have a Speed Limit?" links to an April 2025 dialogue between Ajeya Cotra and Arvind Narayanan. Perhaps you wanted to link the 2023 dialogue between Tamay and Matt Clancy, also on Asterisk?

[-]boazbarak2mo20

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 :)

[-]boazbarak10d222

Students are continuing to post lecture notes on the AI safety course, and I am posting videos on youtube. Students experiments are also posted with the lecture notes: I've been learning a lot from them!

[-]boazbarak2mo*110

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/

[-]boazbarak2mo10

Video is on youtube too

[-]boazbarak1mo*61

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

[-]boazbarak1mo60

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

[-]boazbarak24d20

Wrote one long comment in my non review of IABIED as response to a bunch of other comments.

[-]boazbarak1mo20

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...

Moderation Log

LESSWRONG
LW

LESSWRONG
LW

boazbarak's Shortform

5