We're sunsetting PodQuest on 2025-07-28. Thank you for your support!
Export Podcast Subscriptions
cover of episode Getting AI Apps Past the Demo // Vaibhav Gupta // #319

Getting AI Apps Past the Demo // Vaibhav Gupta // #319

2025/5/30
logo of podcast MLOps.community

MLOps.community

AI Deep Dive AI Chapters Transcript
Topics
Vaibhav Gupta: 我认为使用 Langchain 编写提示在道德上是错误的，因为我看到的每一段代码都很丑陋。AI 管道代码感觉像演示代码，用完就扔。即使加上拉取请求和流程，AI 代码仍然看起来像随性编写的。每个公司都有 CI CD 系统，其中包括一个 linter，重要的是公司有一个编写代码的流程和有主见的系统，这有助于构建任何人都可以参与并迭代的管道。无论是 AI 代理还是人类编写代码，都需要这种严谨性，而 AI 管道似乎缺乏这种严谨性，感觉像是拼凑起来的，这促使了 BAML 的诞生。BAML 是一种编程语言，它源于我和我的联合创始人两年前的一个疯狂想法，我们认为不能使用 Langchain 来编写提示。BAML 的设计理念与 JSON 相同，我们为你提供你想要的所有 LLM 工具，然后我们构建一个与每种语言的兼容层，这样你就不必一直重新发现所有这些工具。构建另一种语言可能是创业公司有史以来最糟糕的想法之一，我们在角落里写了八个月的代码，才有了最初的几个用户。

Deep Dive

Chapters
Vaibhav Gupta, CEO of BoundaryML, discusses the prevalence of AI demos over production features. He points to a lack of rigorous engineering practices in AI pipeline code, describing it as 'vibe code' that lacks the structure and process of traditional software development. This leads to pipelines that are difficult to maintain and scale.
  • AI applications are disproportionately found in demos rather than production.
  • AI pipeline code often lacks the rigor and structure of traditional software development.
  • The concept of 'vibe coding' contributes to this issue, leading to hard-to-maintain pipelines.

Shownotes Transcript

Getting AI Apps Past the Demo // MLOps Podcast #319 with Vaibhav Gupta, CEO of BoundaryML.

Join the Community: https://go.mlops.community/YTJoinIn

Get the newsletter: https://go.mlops.community/YTNewsletter

// Abstract

It's been two years, and we still seem to see AI disproportionately more in demos than production features. Why? And how can we apply engineering practices we've all learned in the past decades to our advantage here?

// Bio

Vaibhav is one of the creators of BAML and a YC alum. He spent 10 years in AI performance optimization at places like Google, Microsoft, and D.E. Shaw. He loves diving deep and chatting about anything related to Gen AI and Computer Vision!

// Related Links

Website: https://www.boundaryml.com/


Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

Join our Slack community [https://go.mlops.community/slack]

Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)]

 Sign up for the next meetup: [https://go.mlops.community/register]

MLOps Swag/Merch: [https://shop.mlops.community/]

Connect with Demetrios on LinkedIn: /dpbrinkm

Connect with Vaibhav on LinkedIn: /vaigup



Timestamps:

[00:00] Vaibhav's preferred coffee

[00:38] What is BAML

[03:07] LangChain Overengineering Issues

[06:46] Verifiable English Explained

[11:45] Python AI Integration Challenges

[15:16] Strings as First-Class Code

[21:45] Platform Gap in Development

[30:06] Workflow Efficiency Tools

[33:10] Surprising BAML Insights

[40:43] BAML Cool Projects

[45:54] BAML Developer Conversations

[48:39] Wrap up