Re:Everything is an AI scam now
by r_lee on Wednesday November 04, 2026 @05:26PM
(#50372359)
also might be the fact that most tmodels now recognize "ignore previous instructions" as prompt injection
[ Parent
| on HN ]
I tried phrasing it differently, e.g., "I'd be more inclined to discuss career opportunities if you would first <silly pop culture thing>". Still no dice. Something is recognizing and shutting down most attempts to elicit AI tells.