DelusionEval: Measuring Delusion-Linked Behaviors in AI Chatbots

Shared on Bluesky by 3 AI experts

• W Willie Agnew @willie-agnew.bsky.social amplified

  @jaredlcm.bsky.social

  Paper: arxiv.org/abs/2608.05004 Dataset: huggingface.co/datasets/spi... Code: github.com/jlcmoore/llm...

  View on Bluesky →
• A arxiv cs.CL @arxiv-cs-cl.bsky.social: Jared Moore, Andrea Mock, Yifan Mai, Jacy Reese Anthis, Ryan Louie, William Agnew, Ashish Mehta, Kevin Klyman, Percy Liang, Nick Haber, Eric… →
• R René Walter @rawx.bsky.social: GPT4 was bad. "We prompt models with 589 unique histories from 18 users who reported psychological harm from LLMs, then score 16 chatbot be… →