Building the future of Negotiations. Shipping code, breaking things, and occasionally writing about it.
10+ years navigating the intersection of cybersecurity, AI/ML, and software development. Currently obsessing over AI agent security and legal AI.
With over 10 years of experience in cybersecurity and software development, I specialize in building secure cloud infrastructure and AI-powered security solutions. My expertise spans cloud security, threat detection, and automation.
My motto: "Adaptability is more important than good planning" — though I also love a good plan.
M.Sc in Cybersecurity & IT Auditing
Temple University
B.A in Film & Media
Temple University
A powerful UI for using LLMs via API. Cheaper, more control, with built-in tool execution.
Interactive web-based Jeopardy! powered by GPT-4 for answer judging and TTS for gameplay.
Secure code execution engine for LLM-generated code with multi-language support.
Prompt injection is a fundamental, unsolved weakness in all LLMs. Learn how certain types of untrustworthy strings can cause AI agents to execute unauthorized tasks.
Read articleThe Model Context Protocol is revolutionizing how AI agents interact with external tools, but this power comes with serious security implications most organizations are overlooking.
Read articleLet's dive into the gritty reality of "vibe coding"—the practice of letting AI write code for you. It's tempting, but here's the catch: this convenience can be a security nightmare.
Read article