Test Guardian - AI Testing Simplified

Kunaal Thanik
  • 5.0(1개의 평가)
  • 과학 기술
  • 매주 업데이트

🎙️ Welcome to Test Guardian – the podcast about testing AI systems that matter. I’m KT, AWS CCP certified, Stanford Deep Learning ML-specialized, and creator of an AI test automation tool. I know how powerful AI can be—and how quickly it can fail without solid testing. Each episode, we dive into real AI failures in healthcare, finance, and more. Discover how bias sneaks in, why perfect data doesn’t exist, and how to build smarter, safer systems. No jargon. No fluff. Just practical insights for testers, developers, and AI-curious minds. Because when AI goes wrong, someone needs to catch it

에피소드

  1. 2025. 05. 28.

    AI and ML are different - really?

    Its biggest misconception if you see AI vs ML. Technically, both are tied to each other. Then what is the difference? Let's find out today in detail.

    16분

  2. 2025. 05. 21.

    Welcome & Introduction

    Hi there! I’m KT - Kunaal Thanik, and this is Test Guardian — the podcast where we explore how to test AI systems so they’re unbiased, safe, fair, and as per regulations. In this episode, I share some real-world stories that show just how important testing is — especially when lives are on the line. You’ll hear about: An AI model that failed to diagnose patients fairly due to biased dataA financial AI that crashed during a market meltdownAnd a hospital chatbot that missed a heart attack because of a typoThese are all true stories — and they all could have been avoided with better testing. Whether you're a tester, developer, or just curious about AI, this episode will help you understand why testers are the unsung heroes of intelligent systems. Hit play, and let’s learn how to guard against AI failures — together.

    8분
  • 2개의 에피소드

소개

🎙️ Welcome to Test Guardian – the podcast about testing AI systems that matter. I’m KT, AWS CCP certified, Stanford Deep Learning ML-specialized, and creator of an AI test automation tool. I know how powerful AI can be—and how quickly it can fail without solid testing. Each episode, we dive into real AI failures in healthcare, finance, and more. Discover how bias sneaks in, why perfect data doesn’t exist, and how to build smarter, safer systems. No jargon. No fluff. Just practical insights for testers, developers, and AI-curious minds. Because when AI goes wrong, someone needs to catch it

정보