用 ASD-STE100 受控语言规范优化 LLM 输出可读性
Karpathy 分享的提示词技巧：让 LLM 按航天文档规范 ASD-STE100 写解释，输出比默认风格好读多了，文末还有可安装的 Skill。
Andrej Karpathy 建议让 LLM 用 ASD-STE100 输出解释内容，这是航空航天领域 1980 年制定的受控语言规范，限定约 900 个批准词汇、53 条写作规则。规则包括每句最多 25 词、一段只讲一个主题、一词一义、主动语态优先。他还会要求'80% 接近 ASD-STE100'来缓和规范的严格程度。作者把这些要求做成了一个学习 Skill，可通过 npx skills add joeseesun/qiaomu-learning 安装，并补充了让 LLM 输出图表、HTML 页面和讲解视频等进阶玩法。
AK 真的是能引领风潮！ 大模型真的啥都懂，专业名词就是最大的Prompt技巧。 ASD-STE100这个名词看着很陌生，最早是航空航天领域 1980 年定的规范。（果然尖端领域有最佳实践） 主要是为了写清晰的技术文档，限定只能用大约 900 个词汇。 写作规则 53 条，挑几个大家感受下： 词汇：只能用批准词汇、技术名词、技术动词，用美式英语拼写。 动词：只能用不定式、祈使式、一般现在/过去/将来时、过去分词（仅作形容词），禁用复杂助动词结构。 描述性写作 ：每句最多25词，每段最多6句，每段只讲一个主题 。 程序性写作：每句最多20词，每句只写一条指令，用祈使句 。 一词一义：词典中每个词只有一个含义、一种词性。例如只用 "start"，不用 "begin"、"commence"。 主动语态优先：禁用被动语态，除非施动者未知。 短句要求：指令最多 20词，描述类最多 25词。 一句一指令：步骤中每句只写一个动作。 受控词汇：约900个批准词 + 公司/项目专用技术名词（需遵守额外规则）。 禁用词汇：缩略语、俚语、地区性表达、同义词混用、复杂动词结构（如 "would have been installed"）。 结构一致性：整篇文档必须使用同一名称。 --- 把这套方法论要求，融入到了一个学习 Skill 中。 安装指令： npx skills add joeseesun/qiaomu-learning Andrej Karpathy @karpathy We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better: Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better: Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better: Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work! In summary: - As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding. - Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised. 🔗 View Quoted Tweet 💬 0 🔄 1 ❤️ 9 👀 1590 📊 3 ⚡
