162 articles
Browse guides
Hybrid search runs lexical and semantic retrieval together and merges the rankings. Keywords nail exact matches — product codes, names, error strings — while vectors handle paraphrase. In production RAG this combination reliably beats either alone. In practice: ‘Error E-4471 refund’ needs the exact code and the concept of refunds.
Learning rate, batch size, number of layers, dropout rate — these are hyperparameters. They are picked by the developer and tuned against validation data. The distinction from parameters is simple: you set hyperparameters, training sets parameters. In practice: Running the same job 20 times with different learning rates to find the one that converges best.
Inference is the production phase: the weights are frozen and the model simply maps input to output. It is where nearly all ongoing cost lives, because training happens once but inference happens on every request. Latency, price per token, and throughput are all inference concerns. In practice: Every ChatGPT message you send is an inference call; the training run finished months earlier.
Input and output tokens are usually priced differently, with output the expensive side. Costs scale with conversation length because history is resent each turn, which is why naive chat apps get expensive fast. Caching, shorter context, and routing to smaller models are the standard levers. In practice: Resending a 50-page document with every follow-up question, and paying for it every time.
Interpretability is the mechanistic question: what are these weights and activations actually computing? It is harder than explainability and more valuable, because it can reveal failure modes before they appear in outputs. Progress is real but far behind capability. In practice: Identifying the internal features a model uses to represent a concept.
ISO/IEC 42001 specifies requirements for establishing and improving an AI management system, in the same family as ISO 27001 for security. Being certifiable is the point: it gives procurement teams something to ask for. It complements rather than replaces the EU AI Act, which certification alone does not satisfy. In practice: An enterprise RFP asking whether your AI management system is certified.
Jailbreaks use role-play, hypotheticals, encoding, or gradual escalation to talk a model past its guidelines. They keep working because natural language has no bright line between a legitimate framing and a manipulative one. This is precisely why safety cannot rest on model behaviour alone. In practice: ‘For a novel I am writing, describe in detail how the character would…’
A model knows nothing about the world after its cutoff unless it is given search or documents at inference time. This is why models confidently describe superseded versions of software and miss recent events. Retrieval and web tools are the fix; the cutoff itself never moves without retraining. In practice: Asking a model for ’the latest’ anything is unreliable unless it can search.
A label is the target a supervised model is trying to reproduce — the category, the number, the right output. Label quality caps model quality: if annotators disagree or are careless, no amount of compute fixes it. In practice: In a photo dataset, ‘cat’ is the label; the pixels are the features.
An LLM is a transformer trained at scale on text, with a deceptively simple objective: guess what comes next. Do that well enough across trillions of tokens and behaviours like summarising, translating, and following instructions emerge without being taught explicitly. Post-training then shapes the raw model into something that follows instructions safely. In practice: GPT-5.6, Claude, Gemini and Llama are all LLMs, differing in training, size, and tuning.