Why the tails come apart

Roles are Mar­tial Arts for Agency

Six Plau­si­ble Meta-Eth­i­cal Alternatives

[meta] Fu­ture mod­er­a­tion and in­ves­ti­ga­tion of down­vote abuse cases, or, I don’t want to deal with this stuff

Hal Fin­ney has just died.

LW client-side com­ment improvements

Mul­ti­ple Fac­tor Ex­pla­na­tions Should Not Ap­pear One-Sided

Quan­tified Risks of Gay Male Sex

[LINK] Speed su­per­in­tel­li­gence?

Changes to my workflow

Fight­ing Bi­ases and Bad Habits like Boggarts

Burdens

An­nounc­ing The Effec­tive Altru­ism Forum

“Fol­low your dreams” as a case study in in­cor­rect thinking

Cre­dence Cal­ibra­tion Ice­breaker Game

Knigh­tian un­cer­tainty: a re­jec­tion of the MMEU rule

Fund­ing can­ni­bal­ism mo­ti­vates con­cern for overheads

[link] Why Psy­chol­o­gists’ Food Fight Matters

Moloch: op­ti­mi­sa­tion, “and” vs “or”, in­for­ma­tion, and sac­ri­fi­cial ems

The Great Filter is early, or AI is hard

Con­nec­tion The­ory Has Less Than No Evidence

Another type of in­tel­li­gence explosion

[LINK] Could a Quan­tum Com­puter Have Sub­jec­tive Ex­pe­rience?

Cal­ibrat­ing your prob­a­bil­ity es­ti­mates of world events: Rus­sia vs Ukraine, 6 months later.

[LINK] Ar­ti­cle in the Guardian about CSER, men­tions MIRI and pa­per­clip AI

MIRI’s 2014 Sum­mer Match­ing Challenge

Knigh­tian Uncer­tainty: Bayesian Agents and the MMEU rule

Ground­work for AGI safety engineering

Sols­tice 2014 /​ Ra­tional Ri­tual Re­treat—A Call to Arms

Every Paul needs a Jesus

An ex­am­ple of deadly non-gen­eral AI

What is the differ­ence be­tween ra­tio­nal­ity and in­tel­li­gence?

Per­sis­tent Idealism

Pro­duc­tivity thoughts from Matt Fallshaw

Me and M&Ms

The metaphor/​myth of gen­eral intelligence

Med­i­ta­tions on Löb’s the­o­rem and prob­a­bil­is­tic logic [LINK]

[Link] Feyn­man lec­tures on physics

[LINK] Eng­ineer­ing Gen­eral In­tel­li­gence (the OpenCog/​CogPrime book)

MIRI 2014 Sum­mer Match­ing Challenge and one-off op­por­tu­nity to donate *for free*

What should a friendly AI do, in this situ­a­tion?

Raven para­dox set­tled to my satisfaction

The dan­gers of dialectic

Maybe we’re not doomed

Causal In­fer­ence Se­quence Part II: Graph­i­cal Models

Why we should err in both directions

Con­ser­va­tion of Ex­pected Jury Probability

Meetup Re­port Thread: Septem­ber 2014

Why hu­mans suck: Rat­ings of per­son­al­ity con­di­tioned on looks, pro­file, and re­ported match

FAI PR track­ing well [link]