Hi I'm Harsh Gupta I'm an undergraduate student studying Mathematics and Computing at IIT Kharagpur, India. I became interested in Rationality when I came across the wikipedia article for Conformational Bias around 2 years ago. That was pretty intriguing, I searched more and read Dan Ariely's book Predictably Irrational. Then also read his other book Upside of Irrationality and now I'm reading hpmor and Khaneman's Thinking Fast and Slow. I also read The Art of Startegy around the same time as Arliey's book and that was a life changer too. The basic backgro...
Eliezer wrote somewhere about what in HPMOR can and what cannot be taken as the author's own views. I forget the exact criterion, but I'm sure it did not include "everything said by HP".
This is mentioned at the beginning of the book
" please keep in mind that, beyond the realm of science, the views of the characters may not be those of the author. Not everything the protagonist does is a lesson in wisdom, and advice offered by darker characters may be untrustworthy or dangerously double-edged."
Fascinating article, my conclusion is that trying to create perfectly aligned LLM will make it easier for LLM to break into the anti-aligned LLM. I would say, alignment folks don't bother. You are accelerating the timelines.