The AI safety community historically has idiosyncratically redefined “black box” to mean“the internals are inexplicable or inauditable” rather than“the internals are inaccessible”.Elsewhere, a…

Posters: davidad. davidad

5 likes recorded by the source corpus.

Topics: AI safety, Epistemics

View Post: https://x.com/davidad/status/1731264964684361816