Is Entertainment Discovery Fundamentally Broken?
This feels like a discovery problem. These platforms are optimization engines for content consumption, not for genuine recommendation. Their goal is to keep you on the service, not to help you find the perfect movie for a rainy Tuesday night.
As a builder, this led me to a prototype (https://lumigo.tv/en-US): what if you could describe your mood or intent in plain language and get a tailored, unbiased shortlist? I've been working on lumigo.tv to test this. The core is an AI agent that you query like, "a thought-provoking sci-fi movie from the 90s" or "a cozy British mystery series." It searches a database of titles and returns matches with ratings and where to stream them.
The technical hypothesis is that a conversational, intent-based search can cut through the noise better than collaborative filtering or genre rows. No ads in results, no promoted titles—just a direct query-to-match engine.
My question to HN isn't about the specific tool, but the broader principle:
Is the dominant "infinite scroll of posters" model the end-state for discovery, or is it a legacy UI that we've just accepted?
Can a neutral, conversational interface ever compete with the billion-dollar optimization of platform-native algorithms?
What would a technically ideal discovery layer look like? Would it be a meta-layer across all services (like a better JustWatch), or is deep integration with one platform's catalog necessary?
I'm sharing this not for feedback on the site itself, but to discuss the architecture of discovery. Is solving the "what to watch" problem more about better data, a better interface, or changing the fundamental incentives away from engagement maximization?
4 comments
[ 2.6 ms ] story [ 21.5 ms ] threadI've always been surprised that Netflix, and other services, don't create "live channels" (e.g "The Office" channel) of their libraries.
Our approach with lumigo.tv is different by necessity, and it's a direct response to the problem you've nailed. We don't use an LLM for knowledge.
Here's the technical split:
The LLM is strictly a query translator. Its only job is to take your messy, natural language prompt ("a gloomy noir set in a rainy city") and convert it into a structured set of searchable tags, genres, and metadata filters. It is forbidden from generating or hallucinating movie titles, actors, or plots. The recommendations come from a structured database. Those translated filters are executed against a traditional database of movies/shows (we've integrated with TMDB and similar sources). The results are ranked by existing metrics like popularity, rating, and release date. The LLM never invents a result; it can only return what exists in the connected data. You're right that pure collaborative filtering (like Netflix's) has a massive data advantage for mainstream tastes. Where it falls short is for edge cases and specific intent. If you want "movies like the third act of Parasite," a collaborative filter has no vector for that. Our hypothesis is that a human can describe that intent, an LLM can map it to tags (e.g., "class tension," "thriller," "dark comedy"), and a database can find matches.
So, it's not AI vs. collaborative filtering. It's AI as a natural-language front-end to a traditional database. The AI handles the "what I want" translation; the database handles the "what exists" retrieval. This avoids the hallucination problem but still allows for queries that a "Because you watched..." algorithm could never process.
Does that distinction make sense? It's an attempt to use each tool for what it's best at.