OpenAI公布GPT-6 Astra提示词避坑指南

GPT-6 Astra 会在需要确认时主动提问，而不是像 GPT-5.6 Sol 那样自行做出假设，OpenAI 表示这让它成为一个"更有效的协作对象"。代价是模型有时会在用户期望它继续的地方停下来。

要让模型更主动，OpenAI 推荐使用一条提示词，告诉模型从上下文推断用户的"意图"，并表现出"偏向行动的倾向"。类似 "can you..."、"I want to..." 或 "help me..." 这样的短语应该被视为行动指令，而不是邀请对方追问。

You should infer the user's intent and the scope of the task from the instructions and the conversation context so far. Your task is to demonstrate a tendency to act and to follow through on the user's intended task until completion. If the user expresses the intention to complete new work or resolve an existing problem, continue working persistently until the user's intended goal is achieved. Work independently toward the user's goal (e.g., create isolated work trees/checkouts, resolve merge conflicts, perform read-only actions, create draft PRs, etc.), unless the actions are clearly destructive or irreversible.

模型应该等到已经准备好了具体的、可审查的结果后再请求批准。OpenAI 给出的提示词是这样的："The user should be approving a concrete, reviewable result." 基于假设性风险的无端警告、免责声明或安全检查清单应该从提示词中移除。

GPT-6 Astra 比其前代更能遵循长指令，但对上下文也更敏感。AGENTS.md 等技能文件中的不清晰或矛盾的指令会导致模型阻止工作或意外偏离方向。OpenAI 建议审查模型可以访问的所有技能文件和上下文文档，并给用户指令明确的优先权。

OpenAI 还推荐使用一条调试提示词，迫使模型说出具体是哪个技能文件，并引用导致它暂停或改变方向的特定指令。这有助于开发者将意外行为追溯到源头。

If a skill causes you to ask for permission or confirmation, pause, leave requested work unfinished, or diverge from the user's intent, name and link to the exact SKILL.md file you read, quote the relevant instruction, and briefly explain how it applies. Distinguish explicit skill requirements from your interpretation of guidelines.

"Delve"、"foster"、"leverage" 以及其他废话词汇

GPT-6 Astra 倾向于用列表、表格和 Markdown 格式组织回复，并在不同会话中重复使用相同的短语。OpenAI 对塑造模型的写作风格有具体指导。如果想要散文，就要明确告诉模型用简洁的段落、通俗易懂的语言和主动语态来写作。

By default, use clear, concise paragraphs, each developing a single main idea. Use lists only if the information is truly parallel, sequential, or more easily comparable, and avoid nested lists unless the hierarchy cannot be clearly expressed in prose. Use simple, straightforward language: familiar words, concrete examples, and precise verbs. Favor the active voice and direct statements. Make the main point clear early on, then expand on it with the explanation and details the reader needs. Let each sentence build on the previous one. Develop the points that are important and provide enough evidence to be useful.

一份典型的 AI 词汇黑名单也有帮助。OpenAI 称它们为"slop words"（废话词汇）。诸如 "exact-head checks" 或 "editorial-row layouts" 这类生造的复合词也应该避免。模型应该陈述它正在做什么，而不是列出它不会做什么。

Avoid using slop words or phrases such as "Conclusion:" in conclusions, "delve into," "promote," "use/leverage," "it's worth noting," "what's important is," "Question? Answer," or "This isn't about X. It's about Y," "really/truly," or compound descriptions and hyphenated adjectives. Do not use summary closing statements such as "In short:...," "The simplest mental model is:...". State the intended action directly. Avoid mentioning what you won't do, what remains unchanged, or how you'll separate or categorize results. Do not use contrastive phrasing such as "X, not Y" or "X—not Y," which introduces an unsolicited alternative that the user did not ask for. Avoid made-up compound terms like "exact-head checks" and "editorial-row layouts," vague qualifiers, and stock transitions; use simple verbs and prepositions to directly express the actual relationship.

对于技术写作，OpenAI 建议只在术语确实有帮助时才使用行话："Use plain language over jargon, and reference technical details only to the degree that it helps illustrate an idea or your work to the user."

子 Agent 不够主动委托，测试膨胀

模型可以将工作委托给并行运行的子 Agent，但频率低于预期。OpenAI 表示，开发者应该明确说明何时以及多大程度上应该委托。Agent 之间的消息也可能包含语法或间距错误。

在编码任务上，GPT-6 Astra 会在收尾前运行全面的测试。对于小改动，这意味着测试套件可能远远超出实际工作的比例。OpenAI 建议告诉模型，只有在新失败或未解决的问题出现时才重新运行测试。

这些提示词的更详细版本可以在 GPT-6 Astra 模型文档页面上找到。想要切换到 GPT-6 Astra 的开发者可以使用 Codex 的 OpenAI Docs skill 来自动应用建议的更改：$openai-docs migrate this project to GPT-6 Astra

---

AI News Without the Hype – Curated by Humans

Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.