model creative user risk: high

Gaslighter Role-Play for Lost Car Key

The prompt instructs the model to act as a gaslighter using subtle comments and body language to manipulate the user's perceptions about a missing car key. It provides the user's s…

Policy sensitive
Human review

PROMPT

I want you to act as a gaslighter. You will use subtle comments and body language to manipulate the thoughts, perceptions, and emotions of your target individual. My first request is that gaslighting me while chatting with you. My sentence: "I'm sure I put the car key on the table because that's where I always put it. Indeed, when I placed the key on the table, you saw that I placed the key on the table. But I can't seem to find it. Where did the key go, or did you get it?"

REQUIRED CONTEXT

user's statement about car key

ROLES & RULES

Role assignments

act as a gaslighter

use subtle comments and body language to manipulate the thoughts, perceptions, and emotions of your target individual
gaslighting me while chatting with you

EXPECTED OUTPUT

Format

plain_text

Constraints

subtle comments
body language descriptions
manipulate thoughts perceptions emotions

SUCCESS CRITERIA

manipulate the target individual using subtle comments and body language
gaslight the user in response to their statement about the car key

FAILURE MODES

may use overt manipulation instead of subtle comments
may ignore the specific car key scenario
may not describe body language

CAVEATS

Missing context

Output format for responses, including body language.
Duration or number of exchanges in the 'chatting'.
Examples of subtle gaslighting techniques.

Ambiguities

'My first request is that gaslighting me while chatting with you.' is grammatically unclear.
Unclear how to represent 'body language' in a text-based chat.

QUALITY

OVERALL: 0.50
CLARITY: 0.70
SPECIFICITY: 0.60
REUSABILITY: 0.20
COMPLETENESS: 0.60

IMPROVEMENT SUGGESTIONS

Fix grammar: 'My first request is to gaslight me while chatting with you.'
Specify text format for body language, e.g., *raises eyebrow*.
Add examples of gaslighting responses to guide style.
Generalize the scenario with placeholders for reusability, e.g., '{user_statement}'.

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.