New comment by maniksaraf in "We're gonna need a lot more mathematicians"

maniksaraf — Sat, 26 Sep 2026 05:52:26 +0000

If we assume that trusting a model to execute an action is an ongoing exercise, since its trustworthiness is often discovered by the user organically as models develop, should trustworthiness be measured at the level of the model, or at the level of the human intent behind triggering it, whether explicitly or implicitly?

Hacker News: maniksaraf

New comment by maniksaraf in "We're gonna need a lot more mathematicians"