Articles
API authentication, rate limits and error handling
An endpoint refuses a request for three different reasons; the response says which.
Automation & AI
Scripting, local inference, infrastructure and AI security.
Articles
Context length, throughput and latency: measuring generation
Four numbers describe a generation; none of them means anything without its conditions.
Articles
GGUF and its runtimes: one file, several engines
GGUF is a container; which engine reads it, and how, is a separate question.
Articles
Inference on CPU and GPU: where the work actually goes
The same model runs on a CPU, a GPU or both; what changes is where the work is done.
Articles
Local models and remote services: where inference actually runs
Where the weights sit decides who operates what, and what leaves your machine.
Articles
Model formats and compatibility: what a weights file has to declare
A weights file is not the model: format, architecture and tokenizer must all line up.
Articles
Model serving and compatible APIs: one endpoint, several contracts
A serving engine adds a queue, a lifecycle and an API surface to a weights file.
Articles
Prompt, context and constraints: what the request envelope decides
The model sees what the envelope builds: template, budget and stopping conditions.
Articles
Quantization: how much precision a model can lose
Fewer bits per weight save memory; what that costs in quality must be measured.
Articles
RAM and VRAM: what has to fit before a model runs
Weights, KV cache and working memory compete for the same pool; fit is arithmetic first.
Articles
Secrets and sensitive data in LLM applications
Two families of sensitive material: the credentials you use and the content you send.
Articles
Streaming, retry, timeout and idempotency
Streaming changes when you know; idempotency decides whether you may ask again.
Articles
Structured JSON output and schema validation
Asking for JSON and constraining the decoder to JSON are two different guarantees.
Articles
AI, machine learning, deep learning and LLMs: what nests inside what
How AI, machine learning, deep learning and LLMs nest — and what each term does not imply.
Articles
The context window and its practical limits
A shared token budget, not durable memory: what the window is and where it runs out.
Articles
What a model knows: embedded knowledge and its limits
What sits in a model's parameters, what its training cutoff freezes, and what you supply.
Articles
Hallucination, uncertainty and verification
Why a fluent model answer can be false, and what checking it actually requires.
Articles
Model, application, workflow, agent: who decides what happens next
Who chooses the next step: the model, the application around it, a workflow or an agent.
Articles
Model, runtime and application: the three layers
The model file, the engine that runs it, the product around it — and what a symptom means.
Articles
Privacy and data disclosure risk when you call an LLM API
What leaves your machine on an API call, what may come back, and the rules that follow.
Articles
Prompts, system instructions and messages
What a prompt and a system instruction are, and why an instruction is not a control.
Articles
Temperature, top-p and output limits
How one token is chosen out of a distribution, and what a token limit actually bounds.
Articles
Tokens, tokenizers and autoregressive generation
Why text becomes tokens, what a tokenizer and vocabulary are, and how generation works.