Maryia Tuleika: Real-Life Guide to AI in Software Testing
summary
Describes using AI on Stockholm public projects with concrete wins and limits: a deployed LLM-agnostic log parser that flags anomalies, routine use of ChatGPT as a tutor, and careful adoption of an AI test pyramid that pushes AI close to code for unit and API test generation while avoiding flaky UI automation. Calls out problems—data scarcity, synthetic data collapse, energy and bias—and argues that thousands of auto-generated test artifacts do not equal better testing without human domain knowledge.
AI-written summary · about
chapters (8)
- 0:00Introduction
- 3:23AI as disruptive force
- 9:09Generative AI limitations
- 16:58AI effectiveness and biases
- 19:20Human role in AI testing
- 23:01AI in testing workflows
- 26:20Where AI excels today
- 27:46Q&A
related talks
32mQuality engineering in the AI age: From testing AI to leveraging GenAI
32m🧐 A Look at Possibilities of Using AI in #SoftwareTesting
44mAI Empowered Software Testing
46mThe Real Impact of AI in Software Testing
55mAI-First Testing
01h 04mImpact of AI on #SoftwareTesting: Are Testers Ready? 🔮
40mFrom Bugs to Brilliance: Leveraging AI in Modern Software Testing
44mHow AI is Exposing the Existential Crisis of Software Testing