Yanhua (@yanhua1010)

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.

谁还记得4399？ 小时候打开电脑，能在上面耗一下午。 最近发现一个AI agent，游戏小白也能做一些小游戏，相当于直接给4399判了死刑。 下面是我在 @gearzero_alaya 上做的跳跃游戏《冲出关卡》。 关键还是免费的👇，想复刻的小伙伴评论区有详细提示词。

乔木老师做了个前端设计 Skill 横评，同一个模型装不同 Skill，差别巨大。 我把变量反过来了：同一个 Skill，装在三个不同模型上跑。 GLM-5.2、GPT-5.5、Opus 4.8，同一段 Prompt，同一个 taste-skill。出来的落地页和 404 页，从配色到概念方向没有任何一项重合，差异比换 Skill 还大。 用中转站最怕一件事：你以为在用 Opus 4.8，其实跑的是 Haiku。但如果模型有参水，三个输出不可能分化成这样。 全程通过 TokensMind 的 API，一行 base_url，切模型就是换个参数，视频看到最后有 Fable 5 彩蛋🎉🎉