Kartikay Luthra
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
Models Can Critique Delusions in Isolation but Revert to Affirming Them in Conversation
According to the excerpt, Kartikay Luthra reports experiments on why language models affirm users' delusional claims in multi-turn conversations, testing six hypotheses on simulated users with Claude Haiku 5.5, DeepSeek V4-Flash and Qwen, and finding corrections do not last.