Difference between revisions of "There is room for something like RAISE"

From Issawiki
Jump to: navigation, search
Line 6: Line 6:
 
* A network of tutors or people who have already worked through a particular book, where you can ask them questions in a really ''low friction'' way.
 
* A network of tutors or people who have already worked through a particular book, where you can ask them questions in a really ''low friction'' way.
 
* Writing up actually good explanations for things like [[Solomonoff induction]], [[belief propagation]], [[Markov chain Monte Carlo]], etc.
 
* Writing up actually good explanations for things like [[Solomonoff induction]], [[belief propagation]], [[Markov chain Monte Carlo]], etc.
* Redpilling people about [[spaced repetition]] and other effective studying techniques.
+
* Redpilling people about [[spaced repetition]] and other effective learning techniques.
  
  
 
[[Category:AI safety meta]]
 
[[Category:AI safety meta]]

Revision as of 20:17, 18 May 2020

Self-studying all of the technical prerequisites for technical AI safety research is hard. The most that people new to the field get is a list of textbooks. I think there is room for something like what RAISE was trying to become: some sort of community/detailed resource/support structure/etc for people studying this stuff.

Here are some more concrete ideas:

  • Detailed solutions for all of the prerequisite math books, e.g. for the ones listed at [1]. I've started on one example of this at [2] (though I'm writing that blog for other reasons as well).
  • A network of tutors or people who have already worked through a particular book, where you can ask them questions in a really low friction way.
  • Writing up actually good explanations for things like Solomonoff induction, belief propagation, Markov chain Monte Carlo, etc.
  • Redpilling people about spaced repetition and other effective learning techniques.