Is Entertainment Discovery Fundamentally Broken?

2 points by nicola_alessi ↗ HN
For the last year, I've been obsessed with a problem: finding something to watch is a chore. The interfaces of Netflix, Prime, and others feel like slot machines designed for maximum engagement, not for matching my mood. The "Because you watched..." algorithms create boring feedback loops, and browsing endless rows of posters is inefficient.

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 ] thread
They need to find a way reinvent "channel surfing". Discovery via "flipping" has lead me to watch things I'd otherwise never would click in an app interface.

I've always been surprised that Netflix, and other services, don't create "live channels" (e.g "The Office" channel) of their libraries.

Your site has a search bar for typing in a full prompt to an LLM about what is my current mood, and I just find it interesting that one's mood is the important thing for your users to supply as input to your service. For me, unless a major event has taken place, I usually don't take time to think much about what's my mood beyond one or two words. If I've been on a journaling kick I'll usually write about the concrete experiences of the day as a proxy for describing my mood without actually getting to what this means for my energy levels/affectations, etc. The mood descriptors I do recognize in myself (eg. kinda sad!) generally factor little into my content consumption decisions (at least consciously). More important to me are questions like "What are folks talking about? (driving discourse online or at the office)", "Which movies have been recommended to me (by friends/family or by advertising)", and "What's accessible? (On a service I already subscribe to without needing an additional purchase)".
Personally I don't believe much in AI recommendations. The problem is the data. AI isn't magic, if the AI doesn't have the data, then it will hallucinate the data. I've discussed with ChatGPT about my movie tastes and asked it to give me recommendations... At first it was a quite interesting conversation, but it couldn't go very far because it knows a lot of details about the blockbuster movies, but strictly nothing about the remaining 98% movies. In comparison, collaborative filtering has access to way more data.
You are 100% correct, and this is the central limitation. An LLM like ChatGPT, trained on general web text, is a terrible movie recommendation engine for exactly the reasons you state. Its knowledge is broad but shallow, skewed toward popular discourse, and it will happily confabulate titles.

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.