How ChatGPT Got Me Drunk
summary
End-to-end cocktail index built in under a day: a web crawler + RabbitMQ queue collects pages, an indexer calls a reverse‑engineered ChatGPT API to extract structured ingredients from noisy HTML, results go into a SQLAlchemy database, and a Flask API + React UI returns cocktails ranked by how many ingredients are available. ChatGPT generates runnable scraper, parsing and schema code but produces mediocre UI and requires human guidance for domain restrictions, deduplication and security review; the prototype works and finds real recipes, completed in roughly 2–3 hours.
AI-written summary · about
chapters (14)
- 0:00Cocktail project introduction
- 2:09ChatGPT for cocktail help
- 3:54RabbitMQ setup with ChatGPT
- 4:57Web crawler with ChatGPT
- 9:17Cocktail recipe indexer
- 11:45Reverse engineering ChatGPT API
- 13:14Extracting recipes with ChatGPT
- 14:15Database schema design
- 16:02Backend API development
- 18:08React frontend development
- 22:44UI design improvements
- 24:07Project lessons learned
- 25:54ChatGPT’s struggles
- 27:44Q&A
related talks
25mChatGPT Unleashed: From Code Wizards To Silly Shenanigans!
01minteresting experience with ChatGPT
39mHow ChatGPT helps to boost your development efficiency
40mChatGPT Widget App from 0 to Production: A Real Story
01h 09mChatGPT and OpenAI API solutions: 👑 My Favourite Implementations
01h 16mChatGPT - and How we Can Benefit from it
59mChatbots - the next UI
25mCan ChatGPT build a Data Platform faster than a developer?