Original Summary

I think a chasm has been crossed. Opus 5.5 few shotted a fully working Figma for me. In the past year I have been trying to benchmark vibe coded apps and see how good they get and this week it did it with very very little guidance from me. I basically just told it reach feature parity.<p>Prior to this vibe coded apps would resemble the real software, this is not a resemblance it&#x27;s the real thing. As a casual Figma user in the past, I can&#x27;t really see a difference. And if there is one you have an LLM that can on the fly operate the app or use it.<p>P.S. I did this is on Mana which is our startup making it easier for LLMs to do it (probably the code is half of what would have been and there are primitives it can use but ultimately it&#x27;s a testament to how good models have gotten). I went on to make google meets, docs, telegram, linear, etc. All basically with single prompts. The biggest jump has been in the UX understanding of models and attention to detail.

  • 情报分类：技术学习与提效
  • 分类依据：内容涉及技术、AI、软件工具或工程实践
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/10/13 02:03:56