Comment by BrianChristian on Reviews of the book 'The Alignment Problem' · 2021-01-20T18:21:49.116Z · LW · GW

Ah, I almost forgot, here's another posted to LessWrong itself:

Review by Ben Hoskin (Larks)

Comment by BrianChristian on Reviews of the book 'The Alignment Problem' · 2021-01-20T03:30:32.933Z · LW · GW

If there’s interest, I’m happy to include a few here (including some from fellow LessWrong users):

Review by The Wall Street Journal

Review by Alison Gopnik

Review by Joshua Gans

Review by Owain Evans (Owain_Evans)

Review by Alex Turner (TurnTrout)

Review by Geoffrey Irving

Review by Toby Ord

Review by Martin Rees

Reviews by Stuart Russell, Jaan Tallinn, and others

Comment by BrianChristian on No nonsense version of the "racial algorithm bias" · 2021-01-20T03:08:28.541Z · LW · GW

>> False negative rate = (false negative)/(actual positive)

>> False positive rate = (false positive)/(actual negative)

 

Correct me if I’m mistaken, but isn’t it:

False negative rate = (false negative)/(false negative + actual positive)

False positive rate = (false positive)/(false positive + actual negative)