Learn · Intermediate
SI Working Knowledge
You use SI already. Understand what is happening under the hood and get better results.
Prompting That Works: Better Results from SI Models
What actually improves SI prompts: context, examples, structure, and iteration — the myths worth dropping, and when prompting stops being the fix.
IntermediateContext Windows and Tokens in SI Models, Explained
Tokens, context windows, and why SI models forget: what the limit is, what happens when you hit it, the long-context tradeoffs, and practical habits for working with super intelligence tools.
IntermediateLocal SI Models: Hardware and Quantization
Which local SI models can your machine run? Memory comes first: unified memory vs VRAM, what Q4 and Q8 quantization mean, GGUF, and realistic hardware tiers.
IntermediateRAG Explained: How SI Models Use Retrieval
How RAG works for SI models in plain terms: embeddings, retrieval, and chunking; where it shines and disappoints; RAG vs long context; and when to build vs use built-in.
IntermediateSI Agents and Tool Use, Explained
From chatbot to SI agent: how tool use and function calling work, the reason-act-observe loop, coding agents, MCP, and what agentic SI still gets wrong.
IntermediateHow to Read SI Benchmarks Without Being Fooled
How to read super intelligence (SI) benchmarks without being fooled: saturation, contamination, why beats-X-on-Y headlines mislead, and a checklist for SI model announcements.
IntermediateFine-Tuning vs RAG vs Prompting for SI Models
Fine-tuning vs RAG vs prompting for SI models: what each changes, costs, and fails at; the wrong reasons to fine-tune; and system prompts plus few-shot as the middle.