Footnote: Looks like MIRI was using “Friendly AI” in our research agenda drafts as of Oct. 23, and we switched to “aligned AI” by Nov. 20 (though we were using phrasings like “reliably aligned with the intentions of its programmers” earlier than that).
Footnote: Looks like MIRI was using “Friendly AI” in our research agenda drafts as of Oct. 23, and we switched to “aligned AI” by Nov. 20 (though we were using phrasings like “reliably aligned with the intentions of its programmers” earlier than that).