Smart Reader - native RSS reading app that suggests interesting news
We all use different kinds of RSS feed readers to fetch news, but as the number of feeds we subscribe to grows, we may wake up to 400+ news items every morning, but very few RSS feed readers can suggest to us what to read first. Smart Reader is a Windows RSS reading app that has a built-in machine learning algorithm for suggesting interesting news. It learns by user's labeling of what news are interesting to them, and as the learning progresses, it will start suggesting among the user's subscribed feeds what it thinks the user might find interesting to read first. Smart Reader also tries to…
What it does
In the maker’s words, at launch
We all use different kinds of RSS feed readers to fetch news, but as the number of feeds we subscribe to grows, we may wake up to 400+ news items every morning, but very few RSS feed readers can suggest to us what to read first. Smart Reader is a Windows RSS reading app that has a built-in machine learning algorithm for suggesting interesting news. It learns by user's labeling of what news are interesting to them, and as the learning progresses, it will start suggesting among the user's subscribed feeds what it thinks the user might find interesting to read first. Smart Reader also tries to provide a consistant, clean view for reading news articles across different domains. Here on the team we have seen some very nice results using Smart Reader. After just one day of training, Smart Reader was able to pick out many interesting articles for us. After about a week of training, the interesting news suggestion has gotten so good for us, we default to reading suggestions before searching all the feeds for interesting news. We would like to share with HN to see what fellow hackers think of this app, and to gather bug reports and insightful feedback. Here are some screenshots: http://dl.dropbox.com/u/69176916/sr1.png http://dl.dropbox.com/u/69176916/sr2.png Here is the readme, with instructions on how to run and train Smart Reader: http://dl.dropbox.com/u/69176916/SmartReaderBeta.pdf Here is the binary for the beta, no installation required, just unzip and run "Smart Reader.exe": http://dl.dropbox.com/u/69176916/SmartReaderBeta.zip The beta app will run till 5/31/12, thanks in advance for all of your time and feedback! You can import your Google Reader subscribed feeds into Smart Reader by importing the OPML file exported from Google Reader.
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, April 2012
the whole month →- MA
Dev tools · 2012 · meteor.com
- IA
Life & fun · 2012 · millionshort.com
- FA
Life & fun · 2012 · firebase.com
- OH
Life & fun · 2012 · kickstarter.com
- IY
Life & fun · 2012 · jamescun.com
- CI
Life & fun · 2012 · clutch.io