MLG 035 Large Language Models 2

MLG 035 Large Language Models 2

From Machine Learning Guide by OCDevel

May 8, 2025 · 45 min · Season 1 · Episode 59

About this episode

This episode discusses the capabilities and mechanisms of large language models, focusing on in-context learning and their application in various tasks.

At inference, large language models use in-context learning with zero-, one-, or few-shot examples to perform new tasks without weight updates, and can be grounded with Retrieval Augmented Generation (RAG) by embedding documents into vector databases for real-time factual lookup using cosine similarity. LLM agents autonomously plan, act, and use external tools via orchestrated loops with persistent memory, while recent benchmarks like GPQA (STEM reasoning), SWE Bench (agentic coding), and MMMU (multimodal college-level tasks) test performance alongside prompt engineering techniques such as chain-of-thought reasoning, structured few-shot prompts, positive instruction framing, and iterative self-correction. Links Notes and resources at ocdevel.com/mlg/mlg35 Build the future of multi-agent software with AGNTCY Try a walking desk stay healthy & sharp while you learn & code In-Context Learning (ICL) Definition: LLMs can perform tasks by learning from examples provided directly in the prompt without updating their parameters. Types: Zero-shot : Direct query, no examples provided. One-shot : Single example provided. Few-shot : Multiple examples, balancing quantity with context window…

Topics covered

  • large language models
  • in-context learning
  • Retrieval Augmented Generation
  • LLM agents
  • prompt engineering
  • performance benchmarks

Keywords

  • large language models
  • in-context learning
  • zero-shot
  • one-shot
  • few-shot
  • Retrieval Augmented Generation
  • prompt engineering

Mentioned in this episode

Organizations: AGNTCY, ocdevel.com

Books & works: MLG 035 Large Language Models 2

More episodes of Machine Learning Guide

Explore listener stats, chart rankings, contacts and more on the Machine Learning Guide podcast page.