flâneur — a map of the web's best reading

How to think about slowing AI — EA Forum

forum.effectivealtruism.org · 2,530 words · saved by 1 readers

Slowing AI[1] is many-dimensional. This post presents variables for determining whether a particular kind of slowing improves safety. Then it applies…

How to think about slowing AI — EA Forum Hide table of contents AI Pause Debate Week How to think about slowing AI by Zach Stein-Perlman Sep 17 2023 4 min read 9 74 AI safety AI Pause Debate (2023) Events on the EA Forum Frontpage How to think about slowing AI Variables Scenarios 9 comments Slowing AI [1] is many-dimensional. This post presents variables for determining whether a particular kind of slowing improves safety. Then it applies those variables to evaluate some often-discussed scenarios. Variables Many variables affect whether an intervention improves AI safety. [2] Here are four cru

Explore this link on the map →

saved by

related reading