Under-the-Hood Mechanics of Generative AI and LLMs for Product Developers

Unlock the black box of Generative AI and LLMs, gaining a deep, practical understanding of their core mechanics to build more innovative and robust products.

The Transformer Architecture: The Brains Behind LLMs

Unit 1: The Genesis of Transformers

Unit 2: Deconstructing Self-Attention

Unit 3: Enhancing Attention & Position

Unit 4: The Transformer's Full Picture

LLM Training and Adaptation Paradigms

Unit 1: The Foundation: Pre-training LLMs

Unit 2: Adapting for Purpose: Fine-tuning LLMs

Unit 3: Efficient Adaptation: Parameter-Efficient Fine-tuning (PEFT)

LLM Inference: From Prompt to Prediction

Unit 1: The Inference Journey Begins

Unit 2: Generating the Next Word

Unit 3: Decoding Strategies: Shaping the Output

Unit 4: Enhancing Inference with External Data

Navigating LLM Limitations and Future Frontiers

Unit 1: Understanding LLM Limitations

Unit 2: Mitigating LLM Limitations

Unit 3: Emerging Frontiers in Generative AI