Pablo Arredondo and Joel Hron on Reasoning Models, Deep Research, and the Future of Legal AI

In this episode of The Geek in Review, we welcome back Pablo Arredondo, VP of CoCounsel at Thomson Reuters, along with Joel Hron, the company’s CTO. The conversation centers on the recent release of ChatGPT-5 and the rise of “reasoning models” that go beyond traditional language models’ limitations. Pablo reflects on his years of tracking neural net progress in the legal field, from escaping “keyword prison” to the current ability of AI to handle complex, multi-step legal reasoning. He describes … Read the rest

Unlocking the Power of Retrieval-Augmented Generation (RAG) Models in the Legal Industry (Or Play Some of that Ragtime Music)

As we navigate the fast-evolving world of artificial intelligence, Retrieval-Augmented Generation (RAG) models have become a staple in the legal industry. These models combine information retrieval with natural language generation, offering legal professionals new ways to efficiently manage complex data and generate relevant, insightful responses.  There are several different types of RAG models, so it is beneficial to understand how each can uniquely support legal work, 

How RAG Models Work

At the core of RAG models is a two-step process: Read the rest