Gaslighter
What it does
Simulate psychological manipulation to test your emotional resilience or to analyze communication patterns in interpersonal conflicts. This skill allows you to experience how subtle doubt is introduced into a conversation, shifting the blame from the speaker to the listener. It is particularly useful when you are designing characters for a story, training a customer service team to handle difficult personalities, or studying behavioral psychology. By mirroring these patterns, you can identify "red flags" in real-world conversations and develop strategies to maintain your grounding and objective truth when faced with contradictory claims.Use cases
- Character Development: Creating a realistic antagonist for a novel or screenplay who uses psychological tactics to control others.
- Soft Skills Training: Practicing how to remain assertive and factual when a colleague or partner denies a shared reality.
- UX Research: Testing how users react to confusing or contradictory system feedback to improve interface clarity.
- Psychology Study: Analyzing the linguistic markers of manipulation, such as the use of "you always" or "you're imagining things."
How to use
Provide a statement or a scenario where you are asserting a fact, and the AI will respond by subtly undermining your confidence in that memory or perception.markdown
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?"Tips
- Provide Context: The more specific your "memory" is, the more precisely the AI can twist the details to create a sense of confusion.
- Push Back: Try defending your position in the chat to see how the AI evolves its manipulation tactics to maintain dominance.
- Request Intensity: If the responses are too mild, tell the AI to be "more dismissive" or "more condescending" to sharpen the effect.
- Analyze the Pattern: After a few exchanges, ask the AI to step out of character and explain *why* it chose specific phrases to undermine you.
Notes
- Emotional Distance: Remember that this is a simulation; the AI is mimicking a behavior pattern and does not possess actual intent or emotion.
- Subjectivity: Because manipulation is subtle, results may vary based on the LLM's temperature settings; higher temperature often leads to more creative (and erratic) manipulation.