Solving AdventOfCode with GitHub Copilot and OpenAI ChatGTP
summary
Live demo of solving Advent of Code puzzles using GitHub Copilot inside an IDE and OpenAI ChatGPT (mainly GPT‑3.5 and GPT‑4). The workflow is to copy‑paste the puzzle into ChatGPT to get runnable Python or Ruby code, use Copilot suggestions in the editor, and iterate by running and debugging; Copilot sometimes produces correct answers without the problem text, while ChatGPT often works immediately on easy puzzles but needs iterative fixes on harder ones. The recommended approach is to combine outputs quickly (copy‑paste prompt, wait a few seconds) and validate results rather than trusting them blindly.
AI-written summary · about
chapters (20)
- 0:00Introduction
- 2:27AdventOfCode challenges
- 4:36GitHub Copilot limits
- 6:25ChatGPT 3.5 Day One
- 9:59Day One part 2 solution
- 11:03Day Two failures
- 13:13Debugging with ChatGPT
- 14:37Days Three and Six
- 15:38Day Five difficulties
- 17:27Days Seven and Eight
- 19:109-day review
- 20:11GitHub Copilot in action
- 21:18Copilot + ChatGPT
- 22:44New GitHub features
- 23:05Tool limits verification
- 24:12Unit tests with AI
- 25:59Guiding AI effectively
- 27:44AI as assistant vs solution
- 29:09Local integration privacy
- 30:36Q&A
related talks
45mSupercharge your coding: Integrating ChatGPT and Copilot in long-term projects
40mUnlocking Productivity with GitHub Copilot Best Practices and Tips
46mAI Integration for Devs: ChatGPT and Copilot in Your Projects
25mImproving developer happiness with AI
01h 00mLevel up with GitHub Copilot: using AI to learn, code, and build
34mAI won't take your job but it sure will help you do it better
40mLevel Up with Copilot
50mGitHub Copilot: Coding Will Never Be The Same Again