15 prompts to audit and wipe everything ChatGPT quietly remembers about you
anthara_ai · x · 2026-11-20
antharaai shared a set of 15 prompts for auditing what ChatGPT's memory feature has quietly built up about you. The author argues ChatGPT studies your patterns from every message to map your personality and habits, and most users have never seen most of that file.
The prompts cover: listing everything it remembers (separating shared facts from assumptions), exposing hidden personality and decision-making profiles with confidence levels, revealing 10 inferences you never directly disclosed, auditing personal data across location/family/work/finances/health, identifying inaccurate or outdated memories with a correction checklist, and tracing which source each detail came from (past chats, memory, custom instructions, or connected apps).
The goal: see how thoroughly you've been modeled, and wipe anything you never agreed to keep.
More from Safety
- Baseten breaks down its security threat model as agent swarms accelerate attacks — baseten · 2026-11-21
- Leaked call: green groups plotted to kill AI bill "under the guise of making it better" — aronchick · 2026-11-21
- OpenAI expands Daybreak security model access for defenders and opens GPT-6 Astra Blue alpha — OpenAIDevs · 2026-11-21
- AI regulation crux: skeptics ask how rules could be abused, not what risks they fix — herbiebradley · 2026-11-21
- OpenAI safety researcher Geoffrey Irving: the speed of AI progress is itself dangerous — geoffreyirving · 2026-11-21
- Jensen Huang doubles down: open models are safer than closed ones, "exactly the opposite" — dansitu · 2026-11-21