Usually when we’re doing it in practice there’s _somewhat_ more awareness of the mechanics than just throwing random obstructions in and hoping for the best.
I mean that seems wild to say to me. Those architectures have documentation and aren't magic black boxes that we chuck inputs at and hope for the best: we do pretty much that with LLMs.
If that's how you optimise, I'm genuinely shocked.
And while the kind of errors hasn’t changed, the quantity and severity of the errors has dropped dramatically in a relatively short span of time.