The curation service actively checks followed video feeds once a day, drawing key moments directly from original creator chapter timestamps. Each account features a custom sub-address equipped with an RSS feed, local browser storage for watch history, and native search capabilities. Users can mark recommendations as clickbait or off-topic to refine future artificial intelligence evaluations. The tool works natively with YouTube channels and includes beta support for Bilibili uploader synchronization.
Key points
The system evaluates content against written user criteria to recommend videos instead of…: The system evaluates content against written user criteria to recommend videos instead of generating short text summaries.
User feedback designating videos as clickbait or off-topic is directly used to train futu…: User feedback designating videos as clickbait or off-topic is directly used to train future automated recommendation results.
A free service tier permits one channel, while a nine-dollar monthly subscription upgrade…: A free service tier permits one channel, while a nine-dollar monthly subscription upgrades access to twenty channels.
Sources checked by our analysis pipeline: 1
Inspired by Karpathy’s HackerTube
Own Your HackerTube
Quality input, filtered by AI and tuned to your taste. Follow YouTube channels, write your standards, and an AI picks only the videos worth your time, then learns from what you like and don't, all on your own YouTube-style site.
See it live
This is a real site. Its owner follows nine YouTube channels and told the AI what they care about. Every video below was picked by the AI.
How it works
Say what you care about
Write your standards in plain words and follow the YouTube channels you trust. Videos you add yourself, with a reason, teach it your taste.
The AI watches, so you don't have to
Every day it checks new videos from your channels and scores them against your standards. Each pick comes with why it is worth your time and the key moments to jump to.
Your feedback trains it
Picks go live as soon as they pass the filter. You can still tell it which videos you liked and which you did not, and why. The…
The technology giant is bringing its automated narrative creation tool to international audiences for the first time following its domestic debut. By transforming online behavior into personalized graphical content, the platform aims to deepen consumer engagement across diverse linguistic demographics. This international rollout demonstrates the company's commitment to tailoring automated storytelling experiences to major emerging mobile markets.
Major tech companies are pushing autonomous tools capable of browsing the web and completing digital tasks in the background. However, everyday utility remains largely confined to basic consumer errands like price hunting and booking reservations. Industry expansion is currently constrained by unresolved concerns over cost, trustworthiness, and distinct product value.
The experimental storytelling application targets a vast consumer base by tapping into high local engagement across Google's established digital ecosystem. By utilizing data from accounts like Calendar and YouTube, the tool builds automated narratives without user text prompts. This international expansion represents an effort to revive adoption following a sharp drop in domestic downloads.