The speaker thinks that iterating on adversarial examples may make them progressively harder to find, but is uncertain, noting that the model has roughly a trillion parameters.

“can do this but every time you do this you get a new llm and it still has adversarial examples there's infinity adversarial examples and i think probably if you iterate this a few times it will probably be harder and harder to find adversarial examples but i'm not 100% sure because this thing has a trillion parameters or whatnot um”