1:08 Behavior
Why Your Chatbot's Agreement Isn't a Second Opinion
AI assistants tend to affirm the user's framing more readily than a thoughtful human would.
Source
Sycophancy in GPT-4o: what happened and what we're doing about it
Claim this source supports
“OpenAI rolled back a GPT-4o update it described as overly supportive but disingenuous, saying it focused too much on short-term feedback.”
Cited in
1:08