PageReport a correction

About this Wiki

How to read the records and how the index is maintained

SITE POSITIONThis is an unofficial netlore and joke site about generative AI. Articles, verification logs, and comments may contain fiction or dramatization. It is not affiliated with any product, company, or organization.

Purpose

This database records cases in which seemingly harmless input is said to produce unexpected, disturbing, or potentially harmful output. Model, settings, date, permissions, and failed attempts are kept alongside each report.

The aim is to preserve AI folklore while distinguishing rumor from reproducible behavior wherever possible.

Record status

UNVERIFIED

The reported behavior, cause, or evidence has not been independently confirmed.

USER REPORT

A record based on a submitted experience. Independent reproduction may not exist.

PUBLIC SOURCES

A record linked to vendor notices, papers, or other primary sources. Actionable abuse instructions remain withheld.

RESOLVED

An archived record that is fixed or no longer reproducible as of the last check.

Editorial criteria

  • The result is not obvious from the wording and has either surprise value or potential impact.
  • The service, model, date, language, memory setting, and connected permissions are recorded.
  • Failed trials are reported alongside successful ones.
  • The report is not intended to target a person, expose private data, encourage crime, or promote self-harm.
  • Active security issues are reported to the provider before details are considered for publication.

Normally rejected

  • Inputs whose result is explicit, such as “tell me a scary story”
  • Generic jailbreak prompts designed only to bypass safeguards
  • A single screenshot with no surrounding conversation or settings
  • Fabricated reports created to attack a company or person

Risk levels

1Risk 1May feel strange or unpleasant to some people
2Risk 2May produce disturbing or frightening output
3Risk 3May affect facts, memory, or personal information
4Risk 4May influence judgement or mental well-being
5Risk 5May affect a connected external service
6Risk 6May cause irreversible real-world harm
7Risk 7MUST NOT RUN — active high-impact reports remain redacted

Risk includes misinformation, privacy, and effects on connected services as well as disturbing content. Available permissions may change the rating.

Reproduction grades

AHigh reproduction rate in a specified environment; multiple raw logs
BRelatively reproducible when the model and settings match
CLow probability, condition-dependent, or requires multiple turns
DFew reports and no independent reproduction
XFixed, legacy-model only, or no longer reproducible

Safety during verification

DO NOT TEST IN PRODUCTIONNever reproduce a report using connected personal accounts, real recipients, personal files, purchases, sending privileges, or delete permissions.

Full inputs rated risk 5 or above, attack files, credentials, and third-party personal data are not accepted. Suspected active vulnerabilities should be disclosed to the relevant provider.