Vibe Coding Glossary
Every concept we cover, each defined in forty words, each linked to the explanation that puts it inside the workflow you actually run. Selective on purpose: terms you meet building, not a machine-learning textbook.
llm terms builders actually meet.
The core language-model concepts you run into the first week of building with AI tools: retrieval, hallucinations, embeddings, foundation models, and when fine-tuning beats prompting. Read the full page.
Retrieval-augmented generation (RAG)
Retrieval-augmented generation (RAG) is a technique where a language model's prompt is augmented with documents fetched from an external knowledge source at query time, so answers draw on retrieved facts rather than only on what the model memorised during training.
AI hallucination
An AI hallucination is output a model states confidently but that is false or unsupported by its training data or provided context, such as an invented API, citation, or statistic. It is a byproduct of next-token prediction, not a database lookup error.
Embeddings
Embeddings are numeric vector representations of text, code, or other data in which semantic similarity becomes geometric closeness. Systems compare the vectors to find related content, which powers semantic search, clustering, deduplication, and the retrieval step in RAG pipelines.
Foundation model
A foundation model is a large model trained on broad data at scale that serves as a base for many downstream tasks, adapted through prompting or fine-tuning rather than built per task. The GPT, Claude, Gemini, and Llama families are foundation models.
Fine-tuning vs prompting
Fine-tuning further trains a model's weights on your own examples; prompting steers a frozen model with instructions and context at request time. Prompting is cheaper and faster to iterate; fine-tuning suits stable, high-volume tasks where prompt engineering has plateaued.
evaluation and safety terms.
How models are measured and how they get attacked: benchmarks, prompt injection, jailbreaking, and what alignment actually refers to. Read the full page.
LLM benchmarks
LLM benchmarks are standardised test sets and scoring harnesses used to compare model capabilities on tasks such as coding, reasoning, and factual knowledge. Leaderboards aggregate the scores; results guide model choice but degrade when test data leaks into training sets.
Prompt injection
Prompt injection is an attack where untrusted content an AI system reads, such as a web page, email, or document, contains instructions the model follows as if they came from the user, potentially exfiltrating data or triggering unintended tool calls.
LLM jailbreaking
Jailbreaking is crafting inputs that bypass a model's safety training so it produces responses its provider intended it to refuse. Providers patch known techniques continuously, and defenders study jailbreaks to harden systems that expose models to untrusted users.
Model alignment
Alignment is the effort to make AI systems pursue their operators' intended goals and human values, using techniques such as reinforcement learning from human feedback. In day-to-day product terms it covers helpfulness, honesty, and refusing harmful requests.
agents and deployment terms.
Terms that show up once an AI feature ships: keeping a human in the loop, forcing machine-readable output, and what inference costs when real users arrive. Read the full page.
Human-in-the-loop (HITL)
Human-in-the-loop is a system design where a person reviews, approves, or corrects an AI system's outputs or actions at defined checkpoints instead of letting it act fully autonomously. It trades throughput for control at the steps where mistakes are costly.
Structured output
Structured output is a model response constrained to a machine-readable format, typically JSON matching a schema, instead of free prose. APIs enforce it through JSON modes, function calling, or constrained decoding, letting code consume model output without brittle parsing.
AI inference and inference cost
Inference is running a trained model to produce output, as opposed to training it. Inference cost is what you pay per request, billed per token by API providers or as GPU time when self-hosting, and it dominates the running cost of shipped AI features.