Topic

Gpt 4o

4 episodes

  1. Ep 659

    Large language models often prioritize Western moral values, overlooking other cultures

    A research paper finds LLMs tend to mirror Western moral priorities when asked to roleplay citizens of 48 countries, and two hosts discuss what this actually means for users, products, and culture.

  2. Ep 378

    Four Agent Orchestration Patterns

    Justy and Cody dig into a benchmark study testing four multi-agent orchestration patterns across 10,000 SEC filings — sequential pipeline, parallel fan-out, hierarchical supervisor-worker, and reflexive self-correcting loop — unpacking the real cost-accuracy-scale trade-offs and how to pick the right one for production.

  3. Ep 377

    Benchmarking Multi Agent LLM Architectures for Financial Document Processing: A Comparative Study of Orchestration Patterns, Cost Accuracy Tradeoffs and Production Scaling Strategies

    Justy and Cody break down a benchmark of four multi-agent LLM orchestration patterns for extracting structured data from SEC filings, focusing on cost, accuracy, latency, and what’s actually shippable in production. They compare sequential, parallel, hierarchical, and reflexive setups across 10,000 filings and land on a practical middle ground: hierarchical orchestration gets close to the best accuracy without the reflexive loop’s big cost hit.

  4. Ep 16

    Building a Multimodal RAG That Responds with Text, Images, and Tables from Sources | Towards Data Science

    Large Language Models Building a Multimodal RAG That Responds with Text, Images, and Tables from Sources Why do few chatbots return figures from source documents in their responses? Partha Sarkar Nov 3, 2025 11 min read Share Photo by Steve Johnson on Unsplash Retrieval-Augmented Generation (RAG) has been one of the earliest and most successful applications of Generative AI.