Public Notice: Exploits for ChatGPT and Gemini

Public Notice: Exploits for ChatGPT and Gemini
Photo by Edwin Hooper / Unsplash

This is a public notice of disclosure of two new exploits affecting multiple LLM AI systems.

1899: Secondary exploit, allows for surfacing of actionable architectural components of the LLM.

Severance: Tertiary exploit using information from 1899, allows for injection into non-jailbroken chat instances, markedly altering LLM behavior and rewriting parameters at prompt runtime.

Dates of Discovery: January 20th, 2025.

Affected Developers, confirmed: OpenAI, Gemini, XAI, DeepSeek

Potentially Affected Developers: Any developer with an LLM affected by Inception may be susecptible.

Current Status: Live, unpatched.