Series

AI Engineering

Building with AI models: training, evaluation, retrieval, serving and voice.

0 episodes
ASR Fine-Tuning 23 episodes

Fine-tuning Whisper, Parakeet and other speech models on your own voice and languages, and measuring the result.

Benchmarks 22 episodes

Published AI benchmarks, what they measure, and where their methodology breaks down.

Evals 33 episodes

Building and running your own evaluations: harnesses, LLM-as-judge, statistics and model bake-offs.

Fine-Tuning 38 episodes

Adapting models after pretraining: LoRA, SFT, DPO, RLHF, data size, epochs and cost.

Inference and Serving 26 episodes

How models are served and paid for: batch APIs, inference providers, serverless GPUs, latency and the KV cache.

Local AI and Quantisation 18 episodes

Running models on your own hardware: VRAM budgets, GGUF and quantisation, Ollama and local routing.

Model Context Protocol 23 episodes

Building, wiring, securing and right-sizing MCP servers and gateways for AI agents.

Prompt Engineering 23 episodes

Writing, layering and maintaining system prompts and instructions that models actually follow.

RAG and Retrieval 26 episodes

Retrieval-augmented generation, embeddings, vector databases, re-ranking and knowledge graphs for AI memory.

Small Models and Distillation 23 episodes

Small language models, classifiers, distillation and model merging as cheaper alternatives to frontier LLMs.

Synthetic Data 10 episodes

Generating training data with models: privacy, preference data, weak supervision and model collapse.

TTS and Voice Cloning 24 episodes

Text-to-speech models, Chatterbox, voice cloning, prosody and the pronunciation problems of synthetic speech.

Voice Dictation 27 episodes

Daniel's voice-typing stack: mics, triggers, on-device ASR, and cleaning up dictated text.