Topics
LLMs
How models work, what they cost, and how to talk to them.
Path
Level
16 pages
- Design an LLM inference platformSystem design · Staff · 38 min
- How an LLM worksAI engineering · Foundation · 9 min
- Tokens, context and costAI engineering · Foundation · 7 min
- Prompting as an interfaceAI engineering · Foundation · 7 min
- Structured output and toolsAI engineering · Core · 8 min
- Context engineering and memoryAI engineering · Senior · 8 min
- Guardrails and prompt injectionAI engineering · Senior · 9 min
- Latency and costAI engineering · Senior · 9 min
- RAG vs fine-tuning vs long contextArticles · Core · 11 min
- Fine-tune a model on your PCArticles · Core · 13 min
- KV vs prompt vs semantic cacheArticles · Senior · 11 min
- FP16 vs INT8 vs INT4Articles · Senior · 11 min
- Reasoning vs standard modelsArticles · Senior · 12 min
- SFT vs RLHF vs DPOArticles · Senior · 12 min
- Dense vs mixture of expertsArticles · Senior · 11 min
- Voice agentsArticles · Senior · 13 min