She has joined the Conspiracy

post by Eliezer Yudkowsky (Eliezer_Yudkowsky) · 2009-01-13T19:48:22.000Z · LW · GW · Legacy · 19 comments


I have no idea whether I had anything to do with this.


Comments sorted by oldest first, as this post is from before comment nesting was available (around 2009-02-27).

comment by chesh · 2009-01-13T20:54:31.000Z · LW(p) · GW(p)

I'd be surprised if you didn't.

comment by Tom_McCabe2 · 2009-01-13T21:00:39.000Z · LW(p) · GW(p)

In case that wasn't a rhetorical question, you almost certainly did: your Introduction to Bayesian Reasoning is the fourth Google hit for "Bayesian", the third Google hit for "Bayes", and has a pagerank of 5, the same as the Cryonics Institute's main website.

comment by Tom3 · 2009-01-13T21:03:16.000Z · LW(p) · GW(p)

"I am 87% confident you will burst into flames"

Ah, at last a practical application of the observation that bayesians cannot agree to disagree.

comment by Eliezer Yudkowsky (Eliezer_Yudkowsky) · 2009-01-13T21:23:57.000Z · LW(p) · GW(p)

I was on a panel with Aaron Diaz (artist) so he certainly knows who I am; the question is whether I actually inspired this in any way. I would hope so, but there are other Bayesians and Diaz has been around for a while.

comment by Cassandra2 · 2009-01-13T21:41:00.000Z · LW(p) · GW(p)

That just made my day there. Very funny!

comment by Gwern_Branwen · 2009-01-14T00:24:56.000Z · LW(p) · GW(p)

Tom: I agree. The last Dungeons & Discourse comic merely had Kimiko as a logical positivist.

comment by Johnicholas · 2009-01-14T02:50:57.000Z · LW(p) · GW(p)

Also, her costume has a hood now, which points pretty directly at "Bayesian Conspiracy" rather than Bayesian in general.

comment by Silas · 2009-01-14T03:10:05.000Z · LW(p) · GW(p)

When I saw the picture, I assumed she was the woman you described in one of your Bayesian conspiracy stories that you post here. But then, she was in a pink jumpsuit, and had, I think, blond hair.

comment by Eliezer Yudkowsky (Eliezer_Yudkowsky) · 2009-01-14T06:29:05.000Z · LW(p) · GW(p)

Silas, she's also described as non-beisutsukai, and pink isn't a Bayesian color.

comment by Aaron_Diaz · 2009-01-14T07:17:17.000Z · LW(p) · GW(p)

Sadly, I didn't know about the Bayesian conspiracy until after I wrote this comic. In fact, I've had the name "Bayesian Empirimancer" in my sketchbook for about a year now until I found an excuse to put it in something. Mainly I just wanted an RPG character that fought using probabilistic confidence.

Of course, Eliezer and I are both Mega Geniuses™, so it should come to no surprise when parallel ideas emerge.

comment by Aron · 2009-01-14T07:22:25.000Z · LW(p) · GW(p)

There still remains some probability that Aaron's recollection is wrong.

comment by Zubon · 2009-01-14T13:09:05.000Z · LW(p) · GW(p)

There are Bayesian and non-Bayesian colors? How confident are you of that?

comment by Gregory_Lemieux · 2009-01-14T22:52:07.000Z · LW(p) · GW(p)

In addition to Tom's analysis I would add the following: A search for "Yudkowski" at the Octogon returns 86 results (although only 23 for "Bayesian"). I was wondering when a Dresden Codak comic would make its way over here!

comment by Jacob_Lyles · 2009-01-15T05:59:23.000Z · LW(p) · GW(p)

As an aspiring applied mathematician, I often think of myself as a "wizard"(student) learning "spells"(mathematical models).

Perhaps I need to start referring to myself by a cooler word like "expirimancer", though my ear for word coinage has never been good.

comment by CannibalSmith2 · 2009-01-15T09:21:07.000Z · LW(p) · GW(p)

So I googled "Bayesian Conspiracy" and found a dozen blog posts all linking to - an overlong article repeating the same thing with numerous examples. I skimmed it in search of the answer to the question "what's the fuss", but didn't find any. So I'll ask here: I get the equation, I get that it's hard to do in your head (what a surprise), but it's just an equation. What's so awe worthy about it? (It's the same with e=mc2, actually.)

comment by Jacob_Lyles · 2009-01-15T20:30:24.000Z · LW(p) · GW(p)


I don't quite get it either. In my line of study, a "Bayesian approach" refers to modeling the conditional posterior probability of the evidence for an event along with the prior probability of the event instead of modeling the conditional likelihood of the event directly. I'm not sure why there is a conspiracy around such a concept.

comment by Cyan2 · 2009-01-15T23:05:38.000Z · LW(p) · GW(p)

CannibalSmith, JacobLyles,

The emphasis on Bayesian probability is because it is the simplest way to extend classical logic to propositions with varying degrees of plausibility. Just as all classical logic can be reduced to repeated applications of modus ponens, all manipulations of plausibility can be reduced to applications of Bayes' Theorem (assuming you want results that will line up with classical logic as the plausibilities approach TRUE and FALSE).

Replies from: FiftyTwo
comment by FiftyTwo · 2011-12-19T20:19:14.628Z · LW(p) · GW(p)

That is one of the best and simplest explanations I've ever heard.

comment by seanearlyaug · 2012-07-12T21:28:39.915Z · LW(p) · GW(p)

I found this site by following a mangled quote in Harry Potter and the Methods of Rationality. Which is a wonderful fanfic.