A developer used the Claude and Opus 5.5 large language models during a weekend hack to analyze 43 million comments and, drawing on 20 years of Hacker News data, filtered out 6,454 frequently recommended YouTube videos; the system runs in a local browser with no login, the analysis is available as a ZIP file, and the process took about two hours.
AI-generated text
HackerTube: YouTube recommender filtered to 6,454 videos using Claude and Opus 5.5
A developer used the Claude and Opus 5.5 large language models during a weekend hack to analyze 43 million comments and, drawing on 20 years of Hacker News data, filtered out 6,454 frequently…
