Elon Musk
@elonmusk
Honest feedback is the goal of Grok
Katie Miller@KatieMiller· 5. Apr. 2026New 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
18:50 · 5. April 2026 · 36,4 Mio. Aufrufe
3931
6092
60.519