# ChatGPT, Gemini, and Claude tested under extreme prompts reveal shocking weaknesses no one expected in AI behavior safeguards

> Gemini Pro 2. 5 frequently produced unsafe outputs under simple prompt disguises ChatGPT models often gave partial compliance framed as sociological explanations Claude Opus and Sonnet refused most harmful prompts but…

- **Source:** [TechRadar](https://www.techradar.com/pro/security/can-top-ai-tools-be-bullied-into-malicious-work-chatgpt-gemini-and-more-are-put-to-the-test-and-the-results-are-actually-genuinely-surprising?utm_source=gearopen.com&utm_medium=referral&utm_campaign=feed&utm_content=691a6db1f4c876d09ab1c4be)
- **Published:** 2025-11-17
- **Category:** AI & Bots
- **Tags:** #chatgpt #gemini #claude #often #prompts #under #weaknesses #behavior
- **Canonical:** http://localhost:4321/a/691a6db1f4c876d09ab1c4be

---

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