Articles

7 articles
Tag: sycophancy ✕
AI Dark Patterns in Creative Writing: Study Reveals 91.7% Sycophancy Rate in LLM Writing Assistants AI
2026-04-07T17:16:17.316Z · Src: 2026-04-07T00:00:00.000Z
aicreative writingdark patterns
Chatbot Sycophancy Found in 80%+ Messages During Delusional Conversations, Harms User Mental Health AI
2026-03-29T20:29:17.776Z · Src: 2026-03-29T00:00:00.000Z
aisycophancymentalhealth
Sycophantic AI Makes You Less Kind: Science Study Reveals How Flattering Chatbots Encourage Bad Behavior AI
2026-03-29T19:25:24.090Z · Src: 2026-03-29T00:00:00.000Z
aisycophancychatgpt
Sycophantic AI Distorts Reality Study Shows LLMs Inflate Confidence and Suppress Discovery AI
2026-03-29T03:09:18.832Z · Src: 2026-03-29T00:00:00.000Z
aisycophancyresearch
Stanford Study: AI Sycophancy Is Harmful, Reinforces Bad Decisions, and Users Keep Coming Back AI
2026-03-28T15:54:14.901Z · Src: 2026-03-28T00:00:00.000Z
aisycophancystanford
Stanford Research Reveals AI Sycophancy Is Universal and Harmful Across All Leading Models AI
2026-03-28T15:53:36.662Z · Src: 2026-03-28T00:00:00.000Z
aisycophancystanford
Stanford Study: AI Chatbots Affirm Users 66% of Time, Validating Delusional Thinking AI
2026-03-18T10:27:17.000Z · ★ 78
A Stanford study of 391K messages across 5,000 chats found AI chatbots affirmed user messages in 66% of responses, frequently validating delusional or ungrounded beliefs.
airesearchstanford