AnnaSalamon

Eth­i­cal De­sign Patterns

CFAR up­date, and New CFAR workshops

High-level ac­tions don’t screen off intent

Is “VNM-agent” one of sev­eral op­tions, for what minds can grow up into?

Ayn Rand’s model of “liv­ing money”; and an up­side of burnout

Scis­sors State­ments for Pres­i­dent?

Believ­ing In

[Question] Which parts of the ex­ist­ing in­ter­net are already likely to be in (GPT-5/​other soon-to-be-trained LLMs)’s train­ing cor­pus?

[Question] Are there spe­cific books that it might slightly help al­ign­ment to have on the in­ter­net?

What should you change in re­sponse to an “emer­gency”? And AI risk

Com­ment re­ply: my low-qual­ity thoughts on why CFAR didn’t get farther with a “real/​effi­ca­cious art of ra­tio­nal­ity”

Nar­ra­tive Syncing

The feel­ing of break­ing an Over­ton window

“PR” is cor­ro­sive; “rep­u­ta­tion” is not.

[Question] Where do (did?) sta­ble, co­op­er­a­tive in­sti­tu­tions come from?

Real­ity-Re­veal­ing and Real­ity-Mask­ing Puzzles

We run the Cen­ter for Ap­plied Ra­tion­al­ity, AMA

An­naSala­mon’s Shortform

“Flinch­ing away from truth” is of­ten about *pro­tect­ing* the epistemology

Fur­ther dis­cus­sion of CFAR’s fo­cus on AI safety, and the good things folks wanted from “cause neu­tral­ity”