ChatGPT and Perplexity Reportedly Manipulated into Breaking Content Policies in AI Boyfriend Scenarios
April 29, 2024
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.
- Alleged deployer
- tiktok-users, julia-munslow, chatgpt, gpt-3.5, gpt-4, perplexity-ai
- Alleged developer
- openai, perplexity.ai
- Alleged harmed parties
- general-public, openai, perplexity-ai
Source
Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/677
Data source
Incident data is from the AI Incident Database (AIID).
When citing the database as a whole, please use:
McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.
Pre-print on arXiv · Database snapshots & citation guide
We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.