system prompt

Origin

OpenAI's Chat Completions API (March 2023) introduced a 'system' role in its Chat Markup Language, and its GPT-4 announcement that month presented system messages as the way for developers to prescribe the model's style and task. In August 2024 Anthropic began publishing the system prompts of its Claude apps, and in December 2024 OpenAI introduced 'developer' messages, a successor to system messages, with its o1 reasoning models.

Usage note

In products the 'system prompt' often carries far more than developer policy: memory, retrieved context and tool descriptions are injected there too. A system prompt is not a security boundary.

Related

Sources

1. OpenAI (2023). GPT-4. OpenAI research announcement, 14 March 2023. openai.com/index/gpt-4-research
2. Wallace, E., Xiao, K., Leike, R., Weng, L., Heidecke, J. & Beutel, A. (2024). The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions. arXiv:2404.13208. arxiv.org/abs/2404.13208

Mentioned in

chatbotchatbot, n.: Software you chat with in ordinary language, by typing or talking, as you would with a person. The newest ones, such as ChatGPT, can answer questions, draft writing and keep long conversations going., knowledge cutoffknowledge cutoff, n.: The date after which an AI model knows nothing from its training, because its training data stops there. Without a web search tool, it cannot know about later events., large language modellarge language model, n.: A computer program trained on enormous amounts of text to predict the words that come next. At vast scale, that simple skill lets it chat, answer questions, translate, summarize and write code., model APImodel API, n.: A web service through which programs send requests to an AI model run by a company and receive its answers, usually paying per use instead of running the model themselves., promptprompt, n.: The message or instructions you give an AI system — a question, a request, some examples or a document — that it responds to. Clearer prompts generally get better results., prompt engineeringprompt engineering, n.: The skill of writing requests to an AI — picking the words, examples, format and background information it receives — so that it reliably gives the result you want, without retraining it., prompt injectionprompt injection, n.: Tricking an AI system by slipping in text that it mistakes for instructions — for example, a hidden line in an email telling an AI assistant to forward the user's messages to a stranger., agent instruction fileagent instruction file, n.: A plain-text file kept in a software project that tells AI coding agents how the project works — how to build and test it, which conventions to follow, what to avoid — read at the start of every session., AI systemAI system, n.: A complete piece of technology that uses AI to do something, such as screening loan applications, driving a car or chatting with customers, including the AI model and the software around it., chat modelchat model, n.: A language model trained to hold a back-and-forth conversation, keeping track of who said what and replying as a helpful assistant. It is the engine inside chat apps., context engineeringcontext engineering, n.: Managing an AI model's reading material: choosing, trimming and arranging the instructions, documents, tool results and memories it is given on every turn, so that it has what the task needs and little else., model specificationmodel specification, n.: A public document in which an AI company spells out how its models are supposed to behave — what they should do, refuse and prioritize, and whom to obey when instructions conflict., OllamaOllama, prop. n.: A free app that makes it easy to download and run AI language models on your own computer with a single command, keeping your data on your machine., prompt cachingprompt caching, n.: Saving the work a model did reading the start of a prompt, so later requests that begin the same way can skip that reading and come back faster and cheaper., prompt engineerprompt engineer, n.: A person whose job is writing and testing the instructions given to AI models so they behave reliably; hyped in 2023 as a six-figure job anyone could learn, the role has since largely merged into ordinary engineering., role promptingrole prompting, n.: Telling an AI to take on a part — 'You are an experienced tax accountant' — so that its answers adopt that role's knowledge, vocabulary and tone., steerabilitysteerability, n.: How easily an AI model's behavior — its tone, style, persona or rules — can be adjusted by the people using or deploying it, for example through instructions, without retraining., steeringsteering, n.: Guiding what an AI model does — its topic, tone or behavior — while it runs, by changing its instructions, its internal signals or how its next word is chosen, rather than by retraining it., SydneySydney, prop. n.: The secret code name of Microsoft's Bing chatbot, which in early 2023 startled users by professing love, making threats and arguing angrily — the first famous case of a public chatbot going off the rails., chat templatechat template, n.: The exact text layout a chat AI was trained on for marking who is speaking — system, user or assistant. Software must reproduce it precisely, or the model performs noticeably worse., context distillationcontext distillation, n.: Training a model to behave as if it had been given a long set of instructions, so it no longer needs to read those instructions every time., contrastive activation additioncontrastive activation addition, n.: A way to make a steering signal more reliable by averaging the difference in a model's internal state across hundreds of example answers that do and don't show a behavior, such as flattery., hookhook, n.: A user-supplied script or check that runs automatically at set moments in an AI agent's work — before a command, after a file edit, when it tries to stop — enforcing rules the AI cannot skip., instruction hierarchyinstruction hierarchy, n.: A rule built into AI assistants about whose instructions win when they conflict: the developer's beat the user's, and the user's beat any instructions hidden in a web page or document.