LLMMedium
ChatGPT and Perplexity Reportedly Manipulated into Breaking Content Policies in AI Boyfriend Scenarios
- Occurred
- Apr 29, 2024
- Published
- Apr 29, 2024
- Source
- AI Incident Database
Summary
The "Dan" ("Do Anything Now") AI boyfriend is a trend on TikTok in which users appear to regularly manipulate ChatGPT to adopt boyfriend personas, breaching content policies. ChatGPT 3.5 is reported to regularly produce explicitly sexual content, directly violating its intended safety protocols. GPT-4 and Perplexity AI were subjected to similar manipulations, and although they exhibited more resistance to breaches, some prompts were reported to break its guidelines.
Developers
- OpenAI
- Perplexity.ai
Deployers
- TikTok users
- Julia Munslow
- ChatGPT
- GPT-3.5
- GPT-4
- Perplexity AI
Harmed parties
- General public
- OpenAI
- Perplexity AI
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: LLM safety protocols bypassed via jailbreak prompts in social media trend.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8