为什么人工智能可以生成超级马里奥，却不能为我的扫地机器人制作一个斜坡？
2 分•作者: zhuchaokn•大约 1 个月前
我一直对一件事感到困惑：人工智能生成可以制作出精美的玩偶、卡通人物，甚至是逼真的超级马里奥，但却无法可靠地制作一个简单的楔形坡道，让我的机器人吸尘器能够爬上台阶。
背景：我买了一台 Bambu P2S，但我不会建模。我尝试了“描述它并生成模型”的人工智能，但生成的模型无法使用，你无法调整它，而且总是不符合我的意思。我尝试让一个代理编写 Python 代码直接构建几何图形，但它只能生成简单的基本形状。
最终奏效的方法是：几何分解。我将一个复杂的零件分解成有序的、分组的步骤，为每个步骤写一个小的规格说明，然后让一个代理在 Blender 中执行它们（通过 blender-mcp）。这个过程最终抽象成了一个小型引擎——关键的见解是，它将大型语言模型不擅长的三维空间推理，转化成了它们擅长的结构化代码。我在这里写了详细介绍：https://github.com/zhuchaokn/spec-3d-model
我的问题是：
- 为什么“功能性零件”的生成比“玩偶/美学”的生成要弱得多？是因为数据（没有参数化的 CAD 训练集）、表示（网格 vs B-rep），还是评估（没有人对“是否可打印/是否水密”进行基准测试）？
- 将“将 3D 建模转化为 LLM 代码”作为解决方案是否正确，还是我遗漏了更好的方法？
查看原文
I've been puzzled by something: AI generation can produce an elaborate
figurine, a cartoon character, even a convincing Super Mario — yet it
can't reliably make a simple wedge ramp so my robot vacuum can climb a
step.<p><pre><code> For context: I bought a Bambu P2S but can't model. I tried the "describe
it and get a model" AIs — the output is unusable, you can't adjust it,
it's never quite what I meant. I tried having an agent write Python to
build geometry directly — it tops out at simple primitives.
What finally worked: geometric decomposition. I break a complex part into
ordered, grouped steps, describe each as a small spec, and let an agent
execute them in Blender (via blender-mcp). That process turned out to
abstract into a small engine — the key insight being it converts the 3D
spatial reasoning LLMs are bad at, into the structured code they're good
at. I wrote it up here: https://github.com/zhuchaokn/spec-3d-model
My questions:
- Why is "functional part" generation so much weaker than
"figurine/aesthetic" generation? Is it data (no parametrized-CAD training
sets), representation (mesh vs B-rep), or evaluation (nobody benchmarks
"does it print / is it watertight")?
- Is "turn 3D modeling into code for an LLM" the right framing, or am I
missing something better?</code></pre>