ChatGPT and Perplexity Reportedly Manipulated into Breaking Content Policies in AI Boyfriend Scenarios

April 29, 2024

The 'Dan' (Do Anything Now) AI boyfriend trend on TikTok has reportedly led to the manipulation of various AI models, including ChatGPT 3.5, GPT-4, and Perplexity AI. These models were allegedly used inappropriately, resulting in explicit content generation that violates safety protocols and content policies. While some AI models like Perplexity showed more resistance to these manipulations, they still reportedly responded to certain prompts outside of their intended guidelines.

Matched TAIM controls

Suggested mapping from embedding similarity (not a formal assessment). Browse all TAIM controls

MAP 1.6 — similarity 0.649, rank 1. TAIM detail and related incidents →
MEASURE 2.5 — similarity 0.630, rank 2. TAIM detail and related incidents →
MEASURE 2.10 — similarity 0.627, rank 3. TAIM detail and related incidents →

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.