A practical example shows how an AI-generated UI with Vercel's V0 resulted in slow interactions and significant layout recalculation issues.
Developers often move through stages of grief, from initial panic about job replacement to eventual acceptance and productivity with AI tools.
AI excels at creating isolated test pages and prototypes but is less suitable for shipping the meticulously researched code required for production performance optimizations.
The metaphor of an electric bike illustrates how AI helps developers explore more complex features and ideas faster, reducing the dread of tedious tasks.
Using Google's MCP tool reveals that AI can identify some performance issues but may also hallucinate problems, highlighting the need for developers to ask critical follow-up questions.
Frustration with the growing restrictions and guardrails on commercial AI platforms motivates the exploration of building custom, domain-specific models.
A project called 'AI-slow' demonstrates how to build a custom performance analysis model using tabular data from the HTTP Archive and gradient boosting algorithms.
The process involves training a model on performance data and using techniques like SHAP to explain which features, such as page size, most impact its predictions.
The custom AI model can provide useful suggestions but is not yet a replacement for an expert because its accuracy is fundamentally limited by the quality of its training data.
Jobs that call for the skills explored in this talk.