[pixelsort]

Working prompt injections for frontier models are devised by applying brilliant pattern constructions. If models ever become useful for writing them, that would represent a massive intelligence leap and a major concern.

As things stand, with working injections becoming harder for humans, people won't be able to make a name for themselves on the internet extracting meth recipes.

My point is just that it isn't a fundamental flaw, or at least, there are indications that reasoning at test time seems to be a part of the remedy.