Hot or Not founder credits 1999 Jester dataset as the pioneer behind collaborative filtering
jfiance · x · 2026-09-27
Hot or Not co-founder James Hong recounts meeting Berkeley professor Ken Goldberg, whose 1999 Jester joke-recommender project pioneered collaborative filtering with 4.1M ratings from 73,421 users. Hong says Hot or Not was originally conceived as a collaborative-filtering dataset for dating, and credits Berkeley's culture of quirky ideas for inspiring it.
More from Companies & People
- OpenAI L7 engineer says he can't build an isolated VLAN with strict egress rules — StewartalsopIII · 2026-09-27
- From Jester to YouTube: How Berkeley Projects Shaped the Modern Web — jfiance · 2026-09-27
- Insider confirms Muse Charm direction: hardware existed, OS3 completes the agentic stack — SimonBalmain · 2026-09-27
- User reports three OpenAI site bugs, gets asked to do free advanced diagnostics — StewartalsopIII · 2026-09-27
- ThePrimeagen joins DHH's Omarchy Core to lead agentic QA with Oligarchy harness — mark_k · 2026-09-27
- OpenAI officially counts down: DevDay is 72 hours away — OpenAIDevs · 2026-09-27