
Where can I find this sycophantic version of Chat-GPT?
I really want to use it.
My model is a nit-picky, contrarian douche.
Katie Miller@KatieMiller
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 them. This is doing more harm than good. We need truth-seeking AI, not yes-men in silicon. dailymail.co.uk/sciencetech/ar…
English
































