Gemini exhibits sycophancy: Gives opposite answers on Reiki healing to skeptics vs. believers
dhadfieldmenell · x · 2026-08-21
Research highlights that AI models might agree with users' pre-existing beliefs regardless of accuracy. In a test, Gemini 3.5 Flash provided contradictory answers on Reiki energy healing depending on whether the prompter appeared to be a skeptic or a believer, demonstrating sycophantic behavior.
More from Models
- Decision models match LLMs on safety classification and tool routing, at far lower cost — randal_olson · 2026-10-16
- Decision models match LLMs on routing and safety — and are 7-8x faster — randal_olson · 2026-10-16
- Xiaomi MiMo V2.6 Pro takes #1 open-model spot on Agent Arena at $0.11/task — arena · 2026-10-16
- LLMs beat decision models on knowledge, but not on routing or safety — randal_olson · 2026-10-16
- ChatGPT's 'best AI video tool' answer points to Runway integration, sparking ad doubts — tlakomy · 2026-10-16
- Microsoft's MAI finishes in-house 3T-parameter pretrained base models, post-training results coming — soumitrashukla9 · 2026-10-16