Show HN: Making a smart TV dumb and then smart

A developer built a replacement smart TV interface after an unwanted webOS update was installed on their TV, writing all of the code with ML models over a couple of weekends to reach a working v1. The developer said the models made the code while they made the design decisions, specifically using WebRTC to cut latency, repurposing vendor logic for buffering voice samples, and designing the user experience. The result lets the developer's daughter navigate the TV by speech while the developer browses on the largest screen at home.

A recent unwanted webOS update that got installed on TV prompted me to start going down the rabbit hole of writing new TV software. After a couple of weekends and massive help from 4 different models, finally managed to get v1 working. My daughter enjoys navigating TV through speech while I get to browse on the biggest screen at home. While all of the code was written by ML models, there were decisions I had to help with. In specific: using WebRTC to cut down latency, repurposing vendor logic for buffering voice samples and designing user experience. It was liberating to finally free the TV of bloatware and make it truly personalized Comments URL: https://news.ycombinator.com/item?id=50202865 https://news.ycombinator.com/item?id=50202865 Points: 2 Comments: 0