Talk Title:

Integrating AI with Retro Hardware: A Commodore 64 LLM Module

Abstract:

In this presentation, we aim to showcase a module that bridges the gap between the past and the future of computing. Our focus is a fully functional cartridge designed for the Commodore 64, equipped with a Large Language Model (LLM) trained on custom datasets derived from a collection of 400 books about the Commodore 64 from the 1980s. This module interfaces with the Commodore 64 as seamlessly as any hardware from the era, operating without the need for cloud connectivity and drawing power from original sources.

The journey began with a world-first: a practical penetration test attack on modern computing systems using an unmodified Commodore 64. Building on this pioneering work, we have developed a module that not only honors the legacy of vintage computing but also demonstrates the potential of integrating sophisticated AI models into retro hardware.

Throughout our talk, we will delve into the engineering challenges while designing and implementing the module. We will explore the selection of hardware components suitable for such intricate electronics and the software development process tailored to this unique environment. Emphasis will be placed on the classic communication protocols and architectural schematics, offering attendees a deep dive into the old-school methods of computer interaction.

By guiding the audience through the development process, we aim to shed light on the intricate balance between leveraging cutting-edge AI technologies and respecting the constraints and capabilities of vintage computing platforms. Our presentation is intended for both enthusiasts of retro computing and professionals interested in the innovative application of artificial intelligence within unconventional contexts.

Speaker Bio:

Konrad Jędrzejczyk is the first man who has ever publicly showcased the unexpanded Commodore 64 as an attacking machine during modern penetration tests. Red Teamer with ten years of Threat Hunting and Incident Response under his belt.

Marek Zmysłowski is senior Security Engineer at Azure DevOps. In the security industry for more than 14 years. Experience in the area of penetration testing, reverse engineering or vulnerability finding. Multiple conference speaker in Poland (Confidence, WTH) and abroad (HiTB, PacSec, DefCamp, H2HC, BlueHat)