Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
July 16, 2025
·
London
HackerNews.coffee: Fast Transparent Personalization
Learn how we built a real-time, transparent recommendation system for Hacker News using fast LLMs, minimal data, and simple user‑editable profiles.
Overview
We built a lean AI recommendation system with transparent user preference profiling for Hacker News. The key AI engineering challenge: real-time personalisation bootstrapped from minimal user data - people don’t want to wait for content, but you still need quality recommendations and it all has to be transparent (and editable) for the user. This talk covers our technical approach, tradeoffs, and extending this to full content ranking.
Links
HomeBrew HN reranks Hacker News content via user preference profiles.
Tech stack