Shaping Open-Source Research with AI-driven tools

In this training, we will explore utilizing artificial intelligence (AI), especially Large Language Models (LLMs), to analyze massive amounts of textual data for open-source research. Leveraging the OsintGPT tool, we will learn functionalities like generating text embeddings and finding similar documents. Created for open-source researchers, journalists, tech enthusiasts, activists, and more, this session aims to highlight AI’s capabilities in the OSINT field. From understanding patterns in narratives to classifying content using topic modeling, we will showcase how AI-powered tools are transforming open-source investigations. Throughout this training, we will take an in-depth look into AI’s potential for empowering open-source research.

This session is most suited for intermediate participants familiar with programming and OSINT command-line tools. However, beginners are also welcome.

Materials

• Access to OpenAI’s API GPT models.
  • https://help.openai.com/en/articles/4936850-where-do-i-find-my-secret-api-key
• OsintGPT tool. The session will run examples using this tool.
  • OsintGPT is a Python package for leveraging OpenAI’s GPT models to analyze text data and perform tasks such as calculating text embeddings, searching for similar documents, and more. https://github.com/estebanpdl/osintgpt
• Reading: Catching up on the weird world of LLMs
  • https://simonwillison.net/2023/Aug/3/weird-world-of-llms/