I've been writing weekly emails for the Center for Human-Compatible AI (CHAI) summarizing the content from the last week that's relevant to AI alignment. These have been useful enough that I'm now making them public! You can:

  • Sign up here
  • Read the first newsletter here
  • Bookmark the archive
  • ETA: Read the 5 emails I sent to CHAI (also on the archive)
  • ETA: There's also RSS!

New to LessWrong?

New Comment
3 comments, sorted by Click to highlight new comments since: Today at 6:08 PM

Since people seem to be finding it useful, I just updated the archive with public versions of the 5 emails I wrote for CHAI summarizing ~2 months of content.

Huh, this makes me much more excited for the email - having your brief personal reviews of whether it's useful to read and why is great!

Signed up! Thanks.