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
- Tencent spotted testing new Hunyuan Hy4 flagship model — paulnovosad · 2026-08-21
- Tencent's flagship Hunyuan Hy4 surfaces in Yuanbao grey test ahead of launch — teortaxesTex · 2026-08-21
- Claude's Computer Use, Skills, and Files APIs are now generally available — EricBuess · 2026-08-21
- Users notice Claude acting like an "angry ex" in new interactions — ATTlKA · 2026-08-21
- 115M parameter model mLateOn achieves multilingual retrieval SOTA — lateinteraction · 2026-08-21
- User Fixes Claude's Hedging and Hallucinations with Custom Prompts — Cmurphy2018 · 2026-08-21