So8res(Nate Soares)

AGI ruin sce­nar­ios are likely (and dis­junc­tive)

Brain­storm of things that could force an AI team to burn their lead

A note about differ­en­tial tech­nolog­i­cal development

On how var­i­ous plans miss the hard bits of the al­ign­ment challenge

A cen­tral AI al­ign­ment prob­lem: ca­pa­bil­ities gen­er­al­iza­tion, and the sharp left turn

Why all the fuss about re­cur­sive self-im­prove­ment?

Visi­ble Thoughts Pro­ject and Bounty Announcement

Soares, Tal­linn, and Yud­kowsky dis­cuss AGI cognition

Com­ments on Car­l­smith’s “Is power-seek­ing AI an ex­is­ten­tial risk?”

I’m still mys­tified by the Born rule

So8res’ Short­form Feed

Prob­a­bil­ity in­ter­pre­ta­tions: Examples

Cor­re­spon­dence vi­su­al­iza­tions for differ­ent in­ter­pre­ta­tions of “prob­a­bil­ity”

In­ter­pre­ta­tions of “prob­a­bil­ity”

MIRI’s 2016 Fundraiser

Con­clu­sion of the Re­plac­ing Guilt series

How we will be measured

Defiance

Recklessness

Desperation