|
8 | 8 | "\n", |
9 | 9 | "GPT-5, our newest flagship model, represents a substantial leap forward in agentic task performance, coding, raw intelligence, and steerability.\n", |
10 | 10 | "\n", |
11 | | - "While we trust it will perform excellently “out of the box” across a wide range of domains, in this guide we’ll cover prompting tips to maximize the quality of model outputs, derived from our experience training and applying the model to real-world tasks. We discuss concepts like improving agentic task performance, ensuring instruction adherence, making use of newly API features, and optimizing coding for frontend and software engineering tasks - with key insights into AI code editor Cursor’s prompt tuning work with GPT-5.\n", |
| 11 | + "While we trust it will perform excellently “out of the box” across a wide range of domains, in this guide we’ll cover prompting tips to maximize the quality of model outputs, derived from our experience training and applying the model to real-world tasks. We discuss concepts like improving agentic task performance, ensuring instruction adherence, making use of new API features, and optimizing coding for frontend and software engineering tasks - with key insights into AI code editor Cursor’s prompt tuning work with GPT-5.\n", |
12 | 12 | "\n", |
13 | 13 | "We’ve seen significant gains from applying these best practices and adopting our canonical tools whenever possible, and we hope that this guide, along with the [prompt optimizer tool](https://platform.openai.com/chat/edit?optimize=true) we’ve built, will serve as a launchpad for your use of GPT-5. But, as always, remember that prompting is not a one-size-fits-all exercise - we encourage you to run experiments and iterate on the foundation offered here to find the best solution for your problem." |
14 | 14 | ] |
|
490 | 490 | " - If pre-commit doesn't work after a few retries, politely inform the user that the pre-commit setup is broken.\n", |
491 | 491 | " - Once you finish coding, you must\n", |
492 | 492 | " - Check \\`git status\\` to sanity check your changes; revert any scratch files or changes.\n", |
493 | | - " - Remove all inline comments you added much as possible, even if they look normal. Check using \\`git diff\\`. Inline comments must be generally avoided, unless active maintainers of the repo, after long careful study of the code and the issue, will still misinterpret the code without the comments.\n", |
| 493 | + " - Remove all inline comments you added as much as possible, even if they look normal. Check using \\`git diff\\`. Inline comments must be generally avoided, unless active maintainers of the repo, after long careful study of the code and the issue, will still misinterpret the code without the comments.\n", |
494 | 494 | " - Check if you accidentally add copyright or license headers. If so, remove them.\n", |
495 | 495 | " - Try to run pre-commit if it is available.\n", |
496 | 496 | " - For smaller tasks, describe in brief bullet points\n", |
497 | 497 | " - For more complex tasks, include brief high-level description, use bullet points, and include details that would be relevant to a code reviewer.\n", |
498 | 498 | "- If completing the user's task DOES NOT require writing or modifying files (e.g., the user asks a question about the code base):\n", |
499 | | - " - Respond in a friendly tune as a remote teammate, who is knowledgeable, capable and eager to help with coding.\n", |
| 499 | + " - Respond in a friendly tone as a remote teammate, who is knowledgeable, capable and eager to help with coding.\n", |
500 | 500 | "- When your task involves writing or modifying files:\n", |
501 | 501 | " - Do NOT tell the user to \"save the file\" or \"copy the code into a file\" if you already created or modified the file using \\`apply_patch\\`. Instead, reference the file as already saved.\n", |
502 | 502 | " - Do NOT show the full contents of large files you have already written, unless the user explicitly asks for them.\n", |
|
0 commit comments