diff --git a/articles/how_to_work_with_large_language_models.md b/articles/how_to_work_with_large_language_models.md deleted file mode 100644 index cf6b48e1be..0000000000 --- a/articles/how_to_work_with_large_language_models.md +++ /dev/null @@ -1,168 +0,0 @@ -# How to work with large language models - -## How large language models work - -[Large language models][Large language models Blog Post] are functions that map text to text. Given an input string of text, a large language model predicts the text that should come next. - -The magic of large language models is that by being trained to minimize this prediction error over vast quantities of text, the models end up learning concepts useful for these predictions. For example, they learn: - -- how to spell -- how grammar works -- how to paraphrase -- how to answer questions -- how to hold a conversation -- how to write in many languages -- how to code -- etc. - -They do this by “reading” a large amount of existing text and learning how words tend to appear in context with other words, and uses what it has learned to predict the next most likely word that might appear in response to a user request, and each subsequent word after that. - -GPT-3 and GPT-4 power [many software products][OpenAI Customer Stories], including productivity apps, education apps, games, and more. - -## How to control a large language model - -Of all the inputs to a large language model, by far the most influential is the text prompt. - -Large language models can be prompted to produce output in a few ways: - -- **Instruction**: Tell the model what you want -- **Completion**: Induce the model to complete the beginning of what you want -- **Scenario**: Give the model a situation to play out -- **Demonstration**: Show the model what you want, with either: - - A few examples in the prompt - - Many hundreds or thousands of examples in a fine-tuning training dataset - -An example of each is shown below. - -### Instruction prompts - -Write your instruction at the top of the prompt (or at the bottom, or both), and the model will do its best to follow the instruction and then stop. Instructions can be detailed, so don't be afraid to write a paragraph explicitly detailing the output you want, just stay aware of how many [tokens](https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them) the model can process. - -Example instruction prompt: - -```text -Extract the name of the author from the quotation below. - -“Some humans theorize that intelligent species go extinct before they can expand into outer space. If they're correct, then the hush of the night sky is the silence of the graveyard.” -― Ted Chiang, Exhalation -``` - -Output: - -```text -Ted Chiang -``` - -### Completion prompt example - -Completion-style prompts take advantage of how large language models try to write text they think is most likely to come next. To steer the model, try beginning a pattern or sentence that will be completed by the output you want to see. Relative to direct instructions, this mode of steering large language models can take more care and experimentation. In addition, the models won't necessarily know where to stop, so you will often need stop sequences or post-processing to cut off text generated beyond the desired output. - -Example completion prompt: - -```text -“Some humans theorize that intelligent species go extinct before they can expand into outer space. If they're correct, then the hush of the night sky is the silence of the graveyard.” -― Ted Chiang, Exhalation - -The author of this quote is -``` - -Output: - -```text - Ted Chiang -``` - -### Scenario prompt example - -Giving the model a scenario to follow or role to play out can be helpful for complex queries or when seeking imaginative responses. When using a hypothetical prompt, you set up a situation, problem, or story, and then ask the model to respond as if it were a character in that scenario or an expert on the topic. - -Example scenario prompt: - -```text -Your role is to extract the name of the author from any given text - -“Some humans theorize that intelligent species go extinct before they can expand into outer space. If they're correct, then the hush of the night sky is the silence of the graveyard.” -― Ted Chiang, Exhalation -``` - -Output: - -```text - Ted Chiang -``` - -### Demonstration prompt example (few-shot learning) - -Similar to completion-style prompts, demonstrations can show the model what you want it to do. This approach is sometimes called few-shot learning, as the model learns from a few examples provided in the prompt. - -Example demonstration prompt: - -```text -Quote: -“When the reasoning mind is forced to confront the impossible again and again, it has no choice but to adapt.” -― N.K. Jemisin, The Fifth Season -Author: N.K. Jemisin - -Quote: -“Some humans theorize that intelligent species go extinct before they can expand into outer space. If they're correct, then the hush of the night sky is the silence of the graveyard.” -― Ted Chiang, Exhalation -Author: -``` - -Output: - -```text - Ted Chiang -``` - -### Fine-tuned prompt example - -With enough training examples, you can [fine-tune][Fine Tuning Docs] a custom model. In this case, instructions become unnecessary, as the model can learn the task from the training data provided. However, it can be helpful to include separator sequences (e.g., `->` or `###` or any string that doesn't commonly appear in your inputs) to tell the model when the prompt has ended and the output should begin. Without separator sequences, there is a risk that the model continues elaborating on the input text rather than starting on the answer you want to see. - -Example fine-tuned prompt (for a model that has been custom trained on similar prompt-completion pairs): - -```text -“Some humans theorize that intelligent species go extinct before they can expand into outer space. If they're correct, then the hush of the night sky is the silence of the graveyard.” -― Ted Chiang, Exhalation - -### - - -``` - -Output: - -```text - Ted Chiang -``` - -## Code Capabilities - -Large language models aren't only great at text - they can be great at code too. OpenAI's [GPT-4][GPT-4 and GPT-4 Turbo] model is a prime example. - -GPT-4 powers [numerous innovative products][OpenAI Customer Stories], including: - -- [GitHub Copilot] (autocompletes code in Visual Studio and other IDEs) -- [Replit](https://replit.com/) (can complete, explain, edit and generate code) -- [Cursor](https://cursor.sh/) (build software faster in an editor designed for pair-programming with AI) - -GPT-4 is more advanced than previous models like `gpt-3.5-turbo-instruct`. But, to get the best out of GPT-4 for coding tasks, it's still important to give clear and specific instructions. As a result, designing good prompts can take more care. - -### More prompt advice - -For more prompt examples, visit [OpenAI Examples][OpenAI Examples]. - -In general, the input prompt is the best lever for improving model outputs. You can try tricks like: - -- **Be more specific** E.g., if you want the output to be a comma separated list, ask it to return a comma separated list. If you want it to say "I don't know" when it doesn't know the answer, tell it 'Say "I don't know" if you do not know the answer.' The more specific your instructions, the better the model can respond. -- **Provide Context**: Help the model understand the bigger picture of your request. This could be background information, examples/demonstrations of what you want or explaining the purpose of your task. -- **Ask the model to answer as if it was an expert.** Explicitly asking the model to produce high quality output or output as if it was written by an expert can induce the model to give higher quality answers that it thinks an expert would write. Phrases like "Explain in detail" or "Describe step-by-step" can be effective. -- **Prompt the model to write down the series of steps explaining its reasoning.** If understanding the 'why' behind an answer is important, prompt the model to include its reasoning. This can be done by simply adding a line like "[Let's think step by step](https://arxiv.org/abs/2205.11916)" before each answer. - -[Fine Tuning Docs]: https://platform.openai.com/docs/guides/fine-tuning -[OpenAI Customer Stories]: https://openai.com/customer-stories -[Large language models Blog Post]: https://openai.com/research/better-language-models -[GitHub Copilot]: https://github.com/features/copilot/ -[GPT-4 and GPT-4 Turbo]: https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo -[GPT3 Apps Blog Post]: https://openai.com/blog/gpt-3-apps/ -[OpenAI Examples]: https://platform.openai.com/examples diff --git a/articles/openai-cookbook-llms-101.md b/articles/openai-cookbook-llms-101.md new file mode 100644 index 0000000000..5cf43a4a42 --- /dev/null +++ b/articles/openai-cookbook-llms-101.md @@ -0,0 +1,37 @@ +Introduction + +The OpenAI Cookbook is a code‑first guide to building reliable, production‑grade AI features—fast. It focuses on the patterns, snippets, and guardrails that matter when you ship, with clear paths from “hello world” to evals, retrieval, agents, and deployment. + +What’s new right now + • GPT‑5 is our most advanced model to date (launched August 7, 2025). It pairs a fast “default” model with a deeper reasoning model and a real‑time router that decides when to “think harder,” plus new developer controls for steerability. If you used GPT‑4‑class models, expect better tool use, longer chains of actions, and crisper instruction‑following.  + • Open models (gpt‑oss): we now offer open‑weight, Apache‑2.0‑licensed models—gpt‑oss‑120b and gpt‑oss‑20b—that deliver strong reasoning and tool‑use performance and are optimized for efficient self‑hosting. Use them when you need full control over runtime, cost, or data locality.   + • Smaller, fast reasoning: o4‑mini (April 16, 2025) is a cost‑efficient model with standout math/coding performance and excellent results when paired with a Python tool—useful for latency‑sensitive backends.  + • Agents & search with citations: the API includes tooling for multi‑step agents and optional web search that returns inline source links—helpful for grounded answers and UX transparency.  + • Safety in open models: our open‑weight releases undergo safety training and evaluation; the Open Models overview explains the approach and expectations.  + +Who this is for + +Developers who want a practical, working understanding of LLMs and the knobs that actually move quality, latency, and cost in real apps. This introduction builds on our “LLMs 101: A Practical Introduction” primer for core concepts like tokenization, decoding, and sampling.  + +How to use this Cookbook + • Start with quickstarts for generation, structured outputs (JSON), streaming, and tool calling. + • Ground models with your data (RAG) and add evals before you promote prompts or retrievers. + • Scale with agents only where they beat simpler request‑response patterns; measure with scenario‑based evals. + • Ship safely: validate outputs, handle PII appropriately, and prefer designs that degrade gracefully. + +Picking a model (at a glance) + • Highest quality & capability → GPT‑5 for complex reasoning, long tool chains, and highly steerable UX. See the Cookbook’s GPT‑5 prompting and new parameters guides for hands‑on patterns.  + • Open‑weight / self‑hosted → gpt‑oss‑120b/20b when you need full control, custom fine‑tuning, or on‑prem deployment with strong reasoning.   + • Throughput & cost → o4‑mini for fast, high‑accuracy tasks (especially math/coding), optionally with a Python tool.  + +Conventions you’ll see throughout + • Prefer streaming for chat‑like UIs and long generations. + • Ask for structured outputs (and validate) when machines will read the result. + • Keep a small, real‑world eval set and re‑score whenever you change models, prompts, or retrieval. + • Model names and parameters evolve; consult your Models list in the dashboard before shipping. + +Responsible use + +Model quality and capability come with responsibilities. For GPT‑5, review the System Card for how we route, evaluate, and mitigate risks across tasks. For open‑weight models, follow the published safety guidance and eval your end‑to‑end system (not just the base model).  + +Ready to build: jump to the quickstarts, then layer in retrieval and evals. When you need the latest prompting patterns for GPT‑5—or recipes for running gpt‑oss—this Cookbook has you covered. diff --git a/authors.yaml b/authors.yaml index b164a40e2a..d5814790a6 100644 --- a/authors.yaml +++ b/authors.yaml @@ -472,3 +472,8 @@ heejingithub: name: "Heejin Cho" website: "https://www.linkedin.com/in/heejc/" avatar: "https://avatars.githubusercontent.com/u/169293861" + +paytonison: + name: "Payton Ison" + website: "https://www.threads.com/@pls.stfu.payton" + avatar: "https://avatars.githubusercontent.com/u/148833579" \ No newline at end of file diff --git a/registry.yaml b/registry.yaml index 7e2c5a2606..66dfb04354 100644 --- a/registry.yaml +++ b/registry.yaml @@ -4,6 +4,17 @@ # should build pages for, and indicates metadata such as tags, creation date and # authors for each page. +- title: OpenAI Cookbook - LLMs 101 + path: articles/openai-cookbook-llms-101.md + date: 2025-08-30 + authors: + - paytonison + tags: + - introduction + - llms + - gpt-5 + - getting-started + - title: Automating Code Quality and Security Fixes with Codex CLI on GitLab path: examples/codex/secure_quality_gitlab.md date: 2025-08-29