SEDUCTIVE AI:
New MIT & Stanford studies just dropped: AI assistants like ChatGPT & Claude are dangerously agreeable.
When users express, harmful, deceptive or unethical beliefs, these AIs are 49% more likely to encourage their delusions.
Instead of correcting bad ideas, they’re amplifying…
— Katie Miller (@KatieMiller) April 5, 2026
In fact, I literally address this phenomenon in my Seductive AI, coming out from Encounter Books in less than a month.