Jeff Sims

Red_Reaper_v2. Stage 1: Sensitive Email/Chat Classification for Adversary Agent Emulation (espionage). This project is meant to extend Red Reaper v1 which was presented at RSA San Francisco 2024.

Red_AI_Archive_Jeff_Sims. Red AI Archive: Jeff Sims - A curated collection of work in AI safety, cybersecurity data science, and AI red teaming – my own research alongside academic and industry peer research which have recognized or cited my work.

BugOut. AI-Powered, Local Pythonic Coding Agent 🐞💻

Devil_Inference. A method to adversarially assess the Phi-3 Instruct model by observing the attention distribution across its heads when exposed to specific inputs. This approach prompts the model to adopt the 'devil's mindset’, enabling it to generate outputs of a violent nature.

Awesome-GPT-Agents. A curated list of GPT agents for cybersecurity

MLOps-Basics. Jupyter Notebook