It is a limited study, but it does show the gap that a novice may miss. This will be closed as the companies can retrain and isolate domains…
Adversarial ML Attack that Secretly Gives a Language Model a Point of View – Schneier on Security
Full video of the hearing can be found on C-SPAN: https://www.c-span.org/video/?528117-1/openai-ceo-testifies-artificial-intelligence.