What is the most dramatic case you've ever seen of someone using a point estimate with a common loss function in a way that had disastrous consequences? (i.e. had they minded the distribution their conclusions / policy Rx would have been different; and, the harm was realized.)
-
Show this thread
-
Like, it's *really* easy to come up with theoretical examples of why distributions matter. But, I want to know if there's any Therac-25 level catastrophes I can cite.
5 replies 0 retweets 2 likesShow this thread -
Replying to @generativist
There’s also the thing with professional dog breeding. Purebred King Charles Spaniels have skulls to small for their brains, so they have seizures and other health issues. Non purebred don’t have these issues, due to introduction of other breed genetics. Distro of genetics :)
1 reply 0 retweets 1 like -
Replying to @SquizzRadical
Oh. Abstract, but interesting!
1 reply 0 retweets 1 like -
Replying to @generativist
Surely your audience appreciates the importance of genetic distribution? :) If we all had the same damn Linux, the world would be a hella boring place. How would you teach pentest without Kali? I can’t totally even.
1 reply 0 retweets 1 like
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.