#llm
- OpenSpec: spec-driven development for AI coding agents
- Harness engineering: the code around the model call
- Building an AutoGPT-style agent in Go
- Building a ReAct agent in Go
- Fine-tuning LLMs: what it is, when you actually need it
- Chain of thought: why thinking out loud helps a model think
- Prompt engineering: what prompts are and how to write good ones
- RAG: retrieval-augmented generation, beyond document chunks
- Context in AI: what it is and how to use it
- Hallucinations in AI: what they are and how to prevent them
- Weights: what a language model actually 'knows'
- The math behind LLMs, mostly without tears
← all tags