I love how tiny the error bars are on so many estimates. https://twitter.com/robertwiblin/status/1244975394668806151 …
-
This Tweet is unavailable.Show this thread
-
+/- 20% are the kinds of error bars you out on, like, a cheap sensor or the output of a well understood model processing good but imperfect inputs. Humans are so wildly over confident in our ability to estimate things and also quantity uncertainty!
1 reply 0 retweets 1 likeShow this thread -
I feel like I saw a great blog post about this but I assumed it was by
@danluu and I can't find it on his blog1 reply 0 retweets 0 likesShow this thread
I agree with you but don't think I have a blog post about this exact thing? The closest thing are probably comments that people often implicitly assume the "happy" path is the only path, which I think is the same fundamental error applied to a different domain.
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.