Karpathy：用图表、网页和讲解视频理解模型输出
我们将花费更多时间试图理解语言模型的输出。一些想法、技巧和窍门：
写作。我取得成功的一个方法：让你的LLM用ASD-STE100来解释某事，这是一种受控语言规范，最初是为航空航天维护文档开发的。LLM对这种语言很熟练，它带有严格的清晰写作风格约束，我经常觉得这样更易读。有时我会试着稍稍缓和它，例如要求“达到ASD-STE100的80%程度”，因为这个规范相当严格。但更好的方法是：
图表/图像。与其写作，让你的LLM创建一个图表。这些内容处理、解析和理解起来要容易得多。但更好的方法是：
网页。要求输出“HTML格式”，以获得一个精美、互动的网页。LLM在前端方面越来越擅长，可以创建精美的体验、动画等。但更好的方法是：
解释视频。我最看好的输出格式是针对任意主题生成的完全定制/量身定制的解释视频。尝试像“为X创建一个3b1b风格的视频解释。用我的ElevenLabs API密钥进行音频叙述”之类的东西。（后者需要一个API密钥，或者你可以让你的LLM为你找到不错的免费替代方案，使用你的本地计算资源）。这实际上开始奏效了！
总之：
- 随着LLM变得更好，它们将自主完成越来越多的基础工作，我们的工作将更多上升到抽象层面的监督和理解。
- 幸运的是，LLM在这里也能帮忙，因为随着智能和代码越来越丰富，你可以要求创建大型、定制、可丢弃的软件产物（例如网页应用、视频解释器），这些在以前是完全没有意义去创建的。在这里大胆尝试，你会感到惊讶。
对照原文
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.