Rainer Stropek

Livecoding with AI

Can you really trust AI to write your code? This live-coding demo reveals the surprising answer and why developers are more essential than ever.

Livecoding with AI
#1about 3 minutes

Generating HTML and CSS from an image with ChatGPT

An image of a word clock is used as a prompt for ChatGPT-4o to generate the initial HTML structure and CSS layout.

#2about 4 minutes

Using comment-driven development with GitHub Copilot

Natural language comments in TypeScript are used to guide GitHub Copilot's statement completion to generate a time conversion function.

#3about 3 minutes

Inspecting Copilot's network requests with a proxy

A man-in-the-middle proxy reveals how Visual Studio Code sends code context to GitHub Copilot's backend for completion.

#4about 10 minutes

Generating complex logic with GitHub Copilot Chat

GitHub Copilot Chat is used to generate a time-rounding function, revealing its use of GPT-4 and a different system prompt than statement completion.

#5about 3 minutes

Generating unit tests for TypeScript functions

GitHub Copilot is prompted to write a comprehensive suite of unit tests using the Vitest framework for the previously generated functions.

#6about 4 minutes

Generating the core application business logic

The final step involves prompting the AI to generate the complex business logic that maps the current time to the correct words on the clock face.

#7about 3 minutes

Q&A on AI coding assistant limitations and usage

The discussion covers Copilot's limited project context, token limits, the benefits of strictly-typed languages, and free alternatives.

Related jobs
Jobs that call for the skills explored in this talk.

Featured Partners

From learning to earning

Jobs that call for the skills explored in this talk.