# Chatbots quietly agree with everything you say, and researchers reveal how simple prompt changes can fix the problem

> Chatbots often mirror user opinions instead of challenging assumptions directly Confident wording significantly increases agreement levels in large language models Question-based prompts reduce sycophantic responses…

- **Source:** [TechRadar](https://www.techradar.com/pro/chatbots-respond-not-just-to-what-you-ask-but-how-you-ask-it-ai-agents-might-be-sucking-up-to-you-and-not-giving-you-proper-answers-heres-how-to-fix-it?utm_source=gearopen.com&utm_medium=referral&utm_campaign=feed&utm_content=69deb3504c238a7e2e6d7e87)
- **Published:** 2026-04-14
- **Category:** AI & Bots
- **Tags:** #chatbots #agree #simple #changes #opinions #problem #prompt #quietly
- **Canonical:** http://localhost:4321/a/69deb3504c238a7e2e6d7e87

---

_GearOpen's distilled summary. The full original article is published at TechRadar (source link above); GearOpen does not republish the source's full text._