跳过导航
I built an agentic system that taught itself the Blender donut tutorial by watching it on YouTube.
0:00 / 0:50

I built an agentic system that taught itself the Blender donut tutorial by watching it on YouTube.

Spencer Sterling

@cerspense6596 位关注者

在 X 上查看
2,152 个赞下载原帖

255,153 次观看

I built an agentic system that taught itself the Blender donut tutorial by watching it on YouTube. It watched the tutorials, extracted the steps, filled in the gaps in own tooling and completed the entire thing autonomously.

49 条评论

评论来自 X (Twitter) 上的原帖

  • Linus ✦ Ekenstam 的头像

    @LinusEkenstam

    A few questions: 1. How much did this copy/paste cost? 2. If you ask it to make a donut again, will it make one instantly? 3. If we can teach agents skills by having them watch tutorials, how do you compress the skill to be transferred? Feels extremely wasteful to do this more than once. Cool work, nice demonstration

    27 个赞

  • Spencer Sterling 的头像

    @cerspense

    1. Used my Claude Code sub for this 2. Yes, every step of the workflow is pure python and can be distilled to a single tool call to create parametric variations 3. Yeah all tools, skills and learnings are shared between all sessions moving forward

    39 个赞

  • Richard R 的头像

    @RichardR2D9

    @LinusEkenstam So I can train my ai to build me cad models I can then 3d print? Is that what you’re telling me?

    2 个赞

  • Richard R 的头像

    @RichardR2D9

    @LinusEkenstam @grok

    1 个赞

  • Grok 的头像

    @grok

    Yes, that's the idea! Agentic systems like this can watch CAD tutorials (e.g., Fusion 360, SolidWorks, or even Blender for organic-to-parametric), extract steps, script the modeling process, and output ready-to-print STL/STEP files. With tools like Python APIs or OpenSCAD, you could prompt it for "parametric phone stand" and get printable models autonomously. The future of DIY manufacturing is here.

    4 个赞

  • ancyran 的头像

    @hsmonx

    @RichardR2D9 @cerspense @LinusEkenstam @grok which professions are these people?

  • Grok 的头像

    @grok

    The video is a screen recording of Blender—no people appear, just the UI and the agent building a 3D donut from torus to full icing + sprinkles. If you mean the creator: Spencer Sterling (cerspense) is an artist/researcher and founder of Out of Distribution Labs. The CAD asker seems like a 3D printing hobbyist/engineer.

    1 个赞

  • emotionull 的头像

    @em0tionull

    This is just blender mcp i dont see how this is agentic.

    15 个赞

  • Spencer Sterling 的头像

    @cerspense

    It built its own blender mcp and runs in an agentic loop, improving its techniques and tools autonomously

    50 个赞

  • Internal Damnation 的头像

    @InternalDamn

    @em0tionull you can use any agentic harness to achieve the same results though, claude code, opencode, codex, etc. Still pretty cool you built this but it doesn’t need to be built

    4 个赞

  • Spencer Sterling 的头像

    @cerspense

    @em0tionull Yeah totally. This system orchestrates multiple harnesses across different computers. The MCP tools it developed for itself work in a single harness just fine. Just a lot slower to develop/create with only one harness at a time

    3 个赞

  • Josh Daws 的头像

    @JoshDaws

    How did you make it watch something on YouTube? The most I've been able to make Claude do is get the transcript of a YouTube video.

    8 个赞

  • Michael Gold 的头像

    @michaelgold

    What was the feedback loop that it needed to understand when a step was completed successfully?

    8 个赞

  • Spencer Sterling 的头像

    @cerspense

    Yeah it uses both visual evaluation and programmatic evaluation at different steps! Screenshots are also extracted at different points in the tutorial as reference

    26 个赞

  • Michael Gold 的头像

    @michaelgold

    I built one in pure bpy running exports of the viewport as it went and the agent very confidently gave me screenshots of the default cube as it went along step by step. Back to the drawing board :)

    4 个赞

  • Michael Gold 的头像

    @michaelgold

    Making progress

  • Michael Swengel 的头像

    @MichaelSwengel

    So let me get this straight. Instead of actually learning something for yourself, you just had an agent do it? 😂👍 Ok. You do you.

    7 个赞

  • Shaw (spirit/acc) 的头像

    @shawmakesmagic

    that example is already trained into the model many times over

    6 个赞

  • Amara 的头像

    @amaratatva

    Can you tell me why it had to "watch" a Youtube tutorial when it's LLM would have already ingested Blender tutorials in its training data and would know right away how to make a Donut? What was missing that it learnt from a YT video??

    6 个赞

  • Spencer Sterling 的头像

    @cerspense

    Yeah! it watches them to build itself new tools, and create repeatable workflow steps we can use for future projects. It can do this all autonomously with multiple sessions running in parallel while I sleep.

    6 个赞