Episode 65 - The chance of something that has never happened before
How can one estimate the probability of an unprecedented event - something that has never happened before - happening? It seems like a hopeless endeavor, but there actually are valid strategies to tackle this problem.
We also recap the interviews that occurred in the 5 previous episodes, and the continuing closure and censorship of our social networks as they are increasingly becoming associated with violence in the real world - and how we're going to get out of this.
Relevant Links
On the continuing problems with the socials’ content policy
NPR: Facebook bans “Dangerous” Individuals
Bloomberg: YouTube ignores Toxic Videos
Medium Article on Instagram’s Rules on Suggestive Content
Popular Front Channel and Podcast “arbitrarily” demonetized for violence when reporting from a war zone
On the probability of rare or unprecedented events
Andrew Gelman on the Probability of having the devisive vote in a US presidential election
Nassim Taleb’s Turkey Problem (I referenced it but my version was a little bit modified)
The Theory that Would Not Die - history of Bayesian Inference from Sharon Bertsch McGrayne
The trinity test - could it have blown up the world?
Safety of High Energy Particle Collisions
Related Episodes
Episode 64 on Resume Tips, mentioned in our interview roundup
Episode 63 with Bethany at USV, mentioned in our interview roundup
Episode 62 with Denish Hearn on The Myth of Capitalism, mentioned in our interview roundup
Episode 61 with Capitalism’ s Michael Bronspegal, mentioned in our interview roundup
Episode 60 with Hilary Mason, mentioned in our interview roundup
Episode 28 on the particular targets of Facebook bans such as Alex Jones
Episode 27 on Fat Tails, which is relevant to the unprecedented event problem
Episode 21 on the philosophy of Probability
Episode 6 on Decentralization getting us out of the Facebook/Social Media Moment
Episode 1 on the Hawaii Missile Scare, and estimating the probability of a real event
Episode 0 on the Foundations of Bayes rule
