Over deze podcast
LLM Primer is a structured deep dive into Large Language Models, based on a seven-book series covering everything from foundational concepts and mathematical intuition to RAG, MCP, scalable AI systems, and AI security.
This podcast is built for engineers and serious professionals who want real understanding—not surface-level explanations.
Each season corresponds to one book. Each episode builds technical clarity step by step.
Understand the model. Build better systems.
Afleveringen
De nieuwste 20 van 23 afleveringen
- Prompt Injection and Jailbreaks · 45 minThis chapter examines prompt injection and jailbreak attacks, which exploit a language model's inherent inability to distinguish between authoritative developer instructions and…
- Data Security and Privacy · 33 minThis chapter examines data security and privacy throughout the LLM lifecycle. It explores the inherent risks of training data, such as copyright issues, personal information…
- Threat Modeling for LLM Systems · 55 minThis chapter adapts traditional threat modeling frameworks (such as STRIDE, PASTA, and attack trees) specifically for the unique vulnerabilities of LLM systems. It guides…
- Why AI Security Is Different · 49 minThis chapter explains that AI security fundamentally and structurally differs from traditional software security. Instead of finding and patching clear bugs in readable source…
- 2-7-7. Hallucinations and Reliability: Managing Confident Errors · 16 minThis episode covers Chapter 7, examining why Large Language Models confidently generate false information. We discuss the probabilistic nature of "hallucinations," the dangerous…
- 2-7-6. Retrieval-Augmented Generation Risks: Securing the Knowledge Pipeline · 35 minThis episode covers Chapter 6, focusing on the security implications of connecting models to external data (RAG). We discuss how this introduces new trust boundaries, the dangers…
- 2-7-5. Input Validation and Output Filtering: The Defense Pipeline · 29 minThis episode covers Chapter 5, detailing how to build disciplined pipelines around an AI model. We discuss strategies for sanitizing user inputs to catch attacks early, the…
- 2-7-4. Prompt Injection and Jailbreaks: Defending the Interpreter · 37 minThis episode explores Chapter 4, detailing how attackers manipulate model behavior through crafted inputs like instruction overrides. We discuss why prompt injection is an…
- 2-7-3. Data Security and Privacy: The AI Lifecycle · 25 minThis episode breaks down Chapter 3, tracking data risks from training to deployment. We discuss how models can memorize sensitive training data, the subtle dangers of leakage…
- 2-7-2. Threat Modeling for LLM Systems: A Step-by-Step Guide · 30 minThis episode covers the systematic approach of Chapter 2, moving beyond vague security worries to concrete risk analysis. We discuss how to identify unique AI assets—like…
- 2-7-1. The Probabilistic Shift: Why AI Security is Different · 36 minThis episode dives into Chapter 1, exploring why traditional security measures fail when applied to Large Language Models. We discuss the fundamental shift from deterministic…
- 2-1-12. The System Architect — Building Your Own LLM System · 39 minIn this episode, we bring every previous concept together to answer the ultimate practical question: How do you actually build a complete LLM system from scratch? We move beyond…
- 2-1-11. The Research Frontier — Cutting-Edge Research · 30 minIn this episode, we look beyond the current generation of models to explore the experimental architectures and learning paradigms that will define the future of AI. We analyze…
- 2-1-10. The Trust Architecture — Safety, Ethics, & Trust · 37 minIn this episode, we address the critical challenge of turning a powerful probabilistic system into a reliable product. We explore why engineering capability must be matched with…
- 2-1-9. The Cost of Intelligence — Performance, Scaling, and Costs · 32 minIn this episode, we face the economic and physical realities of deploying AI. A model’s theoretical capability matters little if it is too slow, too expensive, or too…
- 2-1-8. The Engineering Reality — Using LLMs in Applications · 43 minIn this episode, we step out of the theoretical lab and into the messy reality of production. We explore how a raw Large Language Model is transformed into a reliable product…
- 2-1-7. The Hybrid System — Beyond Next-Token Prediction · 30 minIn this episode, we challenge the idea that Large Language Models are just text generators. We explore how modern AI extends beyond simple prediction to become a reasoning engine…
- 2-1-6. From Generalist to Specialist — Fine-Tuning & Adaptation · 31 minIn this episode, we tackle the critical difference between a model that knows "about" everything and one that can actually do a specific job. We explore the adaptation phase…
- 2-1-5. The Industrial Pipeline — Training Large Models · 31 minIn this episode, we move from the theoretical blueprint of the Transformer to the operational reality of building a Large Language Model. We explore how an empty mathematical…
- 2-1-4. The Blueprint of Intelligence — The Transformer Architecture · 44 minIn this episode, we explore the specific architectural breakthrough that made the current AI revolution possible. We move from general neural network theory to the concrete…








